{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/text-generation/papers/ran/2","list_of":"/task/text-generation","task":"Text Generation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":2,"pages_in_order":7,"rows_per_page":100,"rows":[101,200],"of":610,"counts":{"archive_papers_tagged":5335,"with_a_code_link":2047,"where_syntology_ran_a_sample":610,"not_listed_spam_title":0,"listed":5335,"listed_where_code_ran":610,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":503,"every_run_a_failure_of_syntologys_instrument":107,"listed_with_a_run_with_no_instrument_failure":503,"listed_every_run_a_failure_of_syntologys_instrument":107,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/text-generation/papers/ran/1","prev":"/task/text-generation/papers/ran/1","next":"/task/text-generation/papers/ran/3","papers":[{"url":"/paper/coupling-without-communication-and-drafter","slug":"coupling-without-communication-and-drafter","title":"Coupling without Communication and Drafter-Invariant Speculative Decoding","date":"2024-08-15","arxiv_id":"2408.07978","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/coupling-without-communication-and-drafter#ran","syntology_url":"https://syntology.ai/paper/2408.07978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07978"}},"official":{"repos":["majid-daliri/disd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-robust-and-cost-efficient-knowledge","slug":"towards-robust-and-cost-efficient-knowledge","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","date":"2024-08-13","arxiv_id":"2408.06621","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-robust-and-cost-efficient-knowledge#ran","syntology_url":"https://syntology.ai/paper/2408.06621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06621"}},"official":{"repos":["csm9493/efficient-llm-unlearning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/parallel-speculative-decoding-with-adaptive","slug":"parallel-speculative-decoding-with-adaptive","title":"Parallel Speculative Decoding with Adaptive Draft Length","date":"2024-08-13","arxiv_id":"2408.11850","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/parallel-speculative-decoding-with-adaptive#ran","syntology_url":"https://syntology.ai/paper/2408.11850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11850"}},"official":{"repos":["smart-lty/parallelspeculativedecoding"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-guided-language-modeling","slug":"diffusion-guided-language-modeling","title":"Diffusion Guided Language Modeling","date":"2024-08-08","arxiv_id":"2408.04220","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":11,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-guided-language-modeling#ran","syntology_url":"https://syntology.ai/paper/2408.04220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04220"}},"official":{"repos":["justinlovelace/diffusion-guided-lm"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bias-aware-low-rank-adaptation-mitigating","slug":"bias-aware-low-rank-adaptation-mitigating","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","date":"2024-08-08","arxiv_id":"2408.04556","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bias-aware-low-rank-adaptation-mitigating#ran","syntology_url":"https://syntology.ai/paper/2408.04556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04556"}},"official":{"repos":["cyp-jlu-ai/ba-lora"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-00765","slug":"2408-00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","date":"2024-08-01","arxiv_id":"2408.00765","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-00765#ran","syntology_url":"https://syntology.ai/paper/2408.00765","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00765"}},"official":{"repos":["yuweihao/mm-vet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/paying-more-attention-to-image-a-training","slug":"paying-more-attention-to-image-a-training","title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs","date":"2024-07-31","arxiv_id":"2407.21771","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/paying-more-attention-to-image-a-training#ran","syntology_url":"https://syntology.ai/paper/2407.21771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21771"}},"official":null}},{"url":"/paper/efficient-inference-of-vision-instruction","slug":"efficient-inference-of-vision-instruction","title":"Efficient Inference of Vision Instruction-Following Models with Elastic Cache","date":"2024-07-25","arxiv_id":"2407.18121","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-inference-of-vision-instruction#ran","syntology_url":"https://syntology.ai/paper/2407.18121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18121"}},"official":{"repos":["liuzuyan/elasticcache"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/harmonizing-visual-text-comprehension-and","slug":"harmonizing-visual-text-comprehension-and","title":"Harmonizing Visual Text Comprehension and Generation","date":"2024-07-23","arxiv_id":"2407.16364","repositories_listed":1,"syntology":{"n":18,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/harmonizing-visual-text-comprehension-and#ran","syntology_url":"https://syntology.ai/paper/2407.16364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16364"}},"official":{"repos":["bytedance/textharmony"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/seed-story-multimodal-long-story-generation","slug":"seed-story-multimodal-long-story-generation","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model","date":"2024-07-11","arxiv_id":"2407.08683","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":17,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/seed-story-multimodal-long-story-generation#ran","syntology_url":"https://syntology.ai/paper/2407.08683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08683"}},"official":{"repos":["tencentarc/seed-story"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-internal-states-reveal-hallucination-risk","slug":"llm-internal-states-reveal-hallucination-risk","title":"LLM Internal States Reveal Hallucination Risk Faced With a Query","date":"2024-07-03","arxiv_id":"2407.03282","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llm-internal-states-reveal-hallucination-risk#ran","syntology_url":"https://syntology.ai/paper/2407.03282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03282"}},"official":{"repos":["ziweiji/Internal_States_Reveal_Hallucination"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/conu-conformal-uncertainty-in-large-language","slug":"conu-conformal-uncertainty-in-large-language","title":"ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees","date":"2024-06-29","arxiv_id":"2407.00499","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conu-conformal-uncertainty-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2407.00499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00499"}},"official":{"repos":["zhiyuan-gg/conformal-uncertainty-criterion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/infinigen-efficient-generative-inference-of","slug":"infinigen-efficient-generative-inference-of","title":"InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management","date":"2024-06-28","arxiv_id":"2406.19707","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/infinigen-efficient-generative-inference-of#ran","syntology_url":"https://syntology.ai/paper/2406.19707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19707"}},"official":null}},{"url":"/paper/veriscore-evaluating-the-factuality-of","slug":"veriscore-evaluating-the-factuality-of","title":"VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation","date":"2024-06-27","arxiv_id":"2406.19276","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/veriscore-evaluating-the-factuality-of#ran","syntology_url":"https://syntology.ai/paper/2406.19276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19276"}},"official":{"repos":["Yixiao-Song/VeriScore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/suri-multi-constraint-instruction-following","slug":"suri-multi-constraint-instruction-following","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","date":"2024-06-27","arxiv_id":"2406.19371","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/suri-multi-constraint-instruction-following#ran","syntology_url":"https://syntology.ai/paper/2406.19371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19371"}},"official":{"repos":["chtmp223/suri"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/themis-towards-flexible-and-interpretable-nlg","slug":"themis-towards-flexible-and-interpretable-nlg","title":"Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability","date":"2024-06-26","arxiv_id":"2406.18365","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/themis-towards-flexible-and-interpretable-nlg#ran","syntology_url":"https://syntology.ai/paper/2406.18365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18365"}},"official":{"repos":["PKU-ONELab/Themis"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/can-we-trust-the-performance-evaluation-of","slug":"can-we-trust-the-performance-evaluation-of","title":"Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?","date":"2024-06-25","arxiv_id":"2406.17274","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-we-trust-the-performance-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2406.17274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17274"}},"official":{"repos":["he159ok/benchmark-of-uncertainty-estimation-methods-in-text-summarization"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/variationist-exploring-multifaceted-variation","slug":"variationist-exploring-multifaceted-variation","title":"Variationist: Exploring Multifaceted Variation and Bias in Written Language Data","date":"2024-06-25","arxiv_id":"2406.17647","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/variationist-exploring-multifaceted-variation#ran","syntology_url":"https://syntology.ai/paper/2406.17647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17647"}},"official":{"repos":["dhfbk/variationist"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cascade-reward-sampling-for-efficient","slug":"cascade-reward-sampling-for-efficient","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","date":"2024-06-24","arxiv_id":"2406.16306","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cascade-reward-sampling-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2406.16306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16306"}},"official":{"repos":["lblaoke/CARDS"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-diversity-in-automatic-poetry","slug":"evaluating-diversity-in-automatic-poetry","title":"Evaluating Diversity in Automatic Poetry Generation","date":"2024-06-21","arxiv_id":"2406.15267","repositories_listed":1,"syntology":{"n":14,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":14,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/evaluating-diversity-in-automatic-poetry#ran","syntology_url":"https://syntology.ai/paper/2406.15267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15267"}},"official":{"repos":["hgroener/diversity_in_poetry_generation"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-uncertainty-quantification","slug":"benchmarking-uncertainty-quantification","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","date":"2024-06-21","arxiv_id":"2406.15627","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/benchmarking-uncertainty-quantification#ran","syntology_url":"https://syntology.ai/paper/2406.15627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15627"}},"official":{"repos":["iinemo/lm-polygraph"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/citygpt-empowering-urban-spatial-cognition-of","slug":"citygpt-empowering-urban-spatial-cognition-of","title":"CityGPT: Empowering Urban Spatial Cognition of Large Language Models","date":"2024-06-20","arxiv_id":"2406.13948","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/citygpt-empowering-urban-spatial-cognition-of#ran","syntology_url":"https://syntology.ai/paper/2406.13948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13948"}},"official":{"repos":["tsinghua-fib-lab/citygpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptable-logical-control-for-large-language","slug":"adaptable-logical-control-for-large-language","title":"Adaptable Logical Control for Large Language Models","date":"2024-06-19","arxiv_id":"2406.13892","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/adaptable-logical-control-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.13892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13892"}},"official":{"repos":["joshuacnf/Ctrl-G"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/shield-evaluation-and-defense-strategies-for","slug":"shield-evaluation-and-defense-strategies-for","title":"SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation","date":"2024-06-18","arxiv_id":"2406.12975","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/shield-evaluation-and-defense-strategies-for#ran","syntology_url":"https://syntology.ai/paper/2406.12975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12975"}},"official":{"repos":["xz-liu/shield"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-editing-learning-knowledge-from","slug":"in-context-editing-learning-knowledge-from","title":"In-Context Editing: Learning Knowledge from Self-Induced Distributions","date":"2024-06-17","arxiv_id":"2406.11194","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/in-context-editing-learning-knowledge-from#ran","syntology_url":"https://syntology.ai/paper/2406.11194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11194"}},"official":{"repos":["bigai-ai/ICE"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/fairer-preferences-elicit-improved-human","slug":"fairer-preferences-elicit-improved-human","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","date":"2024-06-17","arxiv_id":"2406.11370","repositories_listed":2,"syntology":{"n":29,"n_ran":20,"n_constructed":4,"n_ran_checked":10,"n_instrument":10,"n_unverified":9,"n_honours":3,"n_violates":2,"n_no_contract":5,"n_pointer_only":2,"phrase":"20 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 2 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/fairer-preferences-elicit-improved-human#ran","syntology_url":"https://syntology.ai/paper/2406.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11370"}},"official":{"repos":["cambridgeltl/zepo"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/analyzing-key-neurons-in-large-language","slug":"analyzing-key-neurons-in-large-language","title":"Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts","date":"2024-06-16","arxiv_id":"2406.10868","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/analyzing-key-neurons-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.10868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10868"}},"official":{"repos":["tigerchen52/qrneuron"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/regularizing-hidden-states-enables-learning","slug":"regularizing-hidden-states-enables-learning","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","date":"2024-06-14","arxiv_id":"2406.10216","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/regularizing-hidden-states-enables-learning#ran","syntology_url":"https://syntology.ai/paper/2406.10216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10216"}},"official":{"repos":["yangrui2015/generalizable-reward-model"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/conme-rethinking-evaluation-of-compositional","slug":"conme-rethinking-evaluation-of-compositional","title":"ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs","date":"2024-06-12","arxiv_id":"2406.08164","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/conme-rethinking-evaluation-of-compositional#ran","syntology_url":"https://syntology.ai/paper/2406.08164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08164"}},"official":{"repos":["jmiemirza/conme"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/on-subjective-uncertainty-quantification-and","slug":"on-subjective-uncertainty-quantification-and","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","date":"2024-06-07","arxiv_id":"2406.05213","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/on-subjective-uncertainty-quantification-and#ran","syntology_url":"https://syntology.ai/paper/2406.05213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05213"}},"official":{"repos":["meta-inf/suq-nlg"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/semantically-diverse-language-generation-for","slug":"semantically-diverse-language-generation-for","title":"Semantically Diverse Language Generation for Uncertainty Estimation in Language Models","date":"2024-06-06","arxiv_id":"2406.04306","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":11,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/semantically-diverse-language-generation-for#ran","syntology_url":"https://syntology.ai/paper/2406.04306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04306"}},"official":{"repos":["ml-jku/SDLG"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/maira-2-grounded-radiology-report-generation","slug":"maira-2-grounded-radiology-report-generation","title":"MAIRA-2: Grounded Radiology Report Generation","date":"2024-06-06","arxiv_id":"2406.04449","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/maira-2-grounded-radiology-report-generation#ran","syntology_url":"https://syntology.ai/paper/2406.04449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04449"}},"official":{"repos":["microsoft/RadFact"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/drivlme-enhancing-llm-based-autonomous","slug":"drivlme-enhancing-llm-based-autonomous","title":"DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences","date":"2024-06-05","arxiv_id":"2406.03008","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/drivlme-enhancing-llm-based-autonomous#ran","syntology_url":"https://syntology.ai/paper/2406.03008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03008"}},"official":{"repos":["sled-group/driVLMe"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/css-contrastive-semantic-similarity-for","slug":"css-contrastive-semantic-similarity-for","title":"CSS: Contrastive Semantic Similarity for Uncertainty Quantification of LLMs","date":"2024-06-05","arxiv_id":"2406.03158","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/css-contrastive-semantic-similarity-for#ran","syntology_url":"https://syntology.ai/paper/2406.03158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03158"}},"official":{"repos":["aoshuang92/css_uq_llms"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/fusionbench-a-comprehensive-benchmark-of-deep","slug":"fusionbench-a-comprehensive-benchmark-of-deep","title":"FusionBench: A Comprehensive Benchmark of Deep Model Fusion","date":"2024-06-05","arxiv_id":"2406.03280","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fusionbench-a-comprehensive-benchmark-of-deep#ran","syntology_url":"https://syntology.ai/paper/2406.03280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03280"}},"official":{"repos":["tanganke/fusion_bench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/patenteval-understanding-errors-in-patent","slug":"patenteval-understanding-errors-in-patent","title":"PatentEval: Understanding Errors in Patent Generation","date":"2024-06-05","arxiv_id":"2406.06589","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/patenteval-understanding-errors-in-patent#ran","syntology_url":"https://syntology.ai/paper/2406.06589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06589"}},"official":{"repos":["zoeyou/patenteval"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/specexec-massively-parallel-speculative","slug":"specexec-massively-parallel-speculative","title":"SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices","date":"2024-06-04","arxiv_id":"2406.02532","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/specexec-massively-parallel-speculative#ran","syntology_url":"https://syntology.ai/paper/2406.02532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02532"}},"official":{"repos":["yandex-research/specexec"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/set-based-prompting-provably-solving-the","slug":"set-based-prompting-provably-solving-the","title":"Order-Independence Without Fine Tuning","date":"2024-06-04","arxiv_id":"2406.06581","repositories_listed":1,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/set-based-prompting-provably-solving-the#ran","syntology_url":"https://syntology.ai/paper/2406.06581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06581"}},"official":{"repos":["reidmcy/set-based-prompting"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/mad-multi-alignment-meg-to-text-decoding","slug":"mad-multi-alignment-meg-to-text-decoding","title":"MAD: Multi-Alignment MEG-to-Text Decoding","date":"2024-06-03","arxiv_id":"2406.01512","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":9,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 2 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mad-multi-alignment-meg-to-text-decoding#ran","syntology_url":"https://syntology.ai/paper/2406.01512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01512"}},"official":{"repos":["neuspeech/mad-meg2text"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/contextualized-sequence-likelihood-enhanced","slug":"contextualized-sequence-likelihood-enhanced","title":"Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation","date":"2024-06-03","arxiv_id":"2406.01806","repositories_listed":1,"syntology":{"n":14,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/contextualized-sequence-likelihood-enhanced#ran","syntology_url":"https://syntology.ai/paper/2406.01806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01806"}},"official":{"repos":["zlin7/contextsl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/are-you-still-on-track-catching-llm-task","slug":"are-you-still-on-track-catching-llm-task","title":"Get my drift? Catching LLM Task Drift with Activation Deltas","date":"2024-06-02","arxiv_id":"2406.00799","repositories_listed":2,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/are-you-still-on-track-catching-llm-task#ran","syntology_url":"https://syntology.ai/paper/2406.00799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00799"}},"official":{"repos":["microsoft/TaskTracker"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-aspect-controllable-text-generation","slug":"multi-aspect-controllable-text-generation","title":"Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation","date":"2024-05-30","arxiv_id":"2405.19958","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-aspect-controllable-text-generation#ran","syntology_url":"https://syntology.ai/paper/2405.19958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19958"}},"official":{"repos":["nju-websoft/magic"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kernel-language-entropy-fine-grained","slug":"kernel-language-entropy-fine-grained","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","date":"2024-05-30","arxiv_id":"2405.20003","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kernel-language-entropy-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2405.20003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20003"}},"official":{"repos":["alexandervnikitin/kernel-language-entropy"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-large-language-model-biases-in","slug":"evaluating-large-language-model-biases-in","title":"Evaluating Large Language Model Biases in Persona-Steered Generation","date":"2024-05-30","arxiv_id":"2405.20253","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/evaluating-large-language-model-biases-in#ran","syntology_url":"https://syntology.ai/paper/2405.20253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20253"}},"official":{"repos":["andyjliu/persona-steered-generation-bias"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/language-generation-with-strictly-proper","slug":"language-generation-with-strictly-proper","title":"Language Generation with Strictly Proper Scoring Rules","date":"2024-05-29","arxiv_id":"2405.18906","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-generation-with-strictly-proper#ran","syntology_url":"https://syntology.ai/paper/2405.18906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18906"}},"official":{"repos":["shaochenze/scoringruleslm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/glauber-generative-model-discrete-diffusion","slug":"glauber-generative-model-discrete-diffusion","title":"Glauber Generative Model: Discrete Diffusion Models via Binary Classification","date":"2024-05-27","arxiv_id":"2405.17035","repositories_listed":0,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glauber-generative-model-discrete-diffusion#ran","syntology_url":"https://syntology.ai/paper/2405.17035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17035"}},"official":null}},{"url":"/paper/on-the-noise-robustness-of-in-context","slug":"on-the-noise-robustness-of-in-context","title":"On the Noise Robustness of In-Context Learning for Text Generation","date":"2024-05-27","arxiv_id":"2405.17264","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/on-the-noise-robustness-of-in-context#ran","syntology_url":"https://syntology.ai/paper/2405.17264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17264"}},"official":{"repos":["ml-stat-sustech/local-perplexity-ranking"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-algorithmic-bias-of-aligning-large","slug":"on-the-algorithmic-bias-of-aligning-large","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","date":"2024-05-26","arxiv_id":"2405.16455","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/on-the-algorithmic-bias-of-aligning-large#ran","syntology_url":"https://syntology.ai/paper/2405.16455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16455"}},"official":{"repos":["JiancongXiao/PM_RLHF"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-jailbreaking-of-the-text-to-image","slug":"automatic-jailbreaking-of-the-text-to-image","title":"Automatic Jailbreaking of the Text-to-Image Generative AI Systems","date":"2024-05-26","arxiv_id":"2405.16567","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/automatic-jailbreaking-of-the-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2405.16567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16567"}},"official":{"repos":["Kim-Minseon/APGP"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vb-lora-extreme-parameter-efficient-fine","slug":"vb-lora-extreme-parameter-efficient-fine","title":"VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks","date":"2024-05-24","arxiv_id":"2405.15179","repositories_listed":1,"syntology":{"n":17,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":17,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vb-lora-extreme-parameter-efficient-fine#ran","syntology_url":"https://syntology.ai/paper/2405.15179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15179"}},"official":{"repos":["leo-yangli/vb-lora"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sirllm-streaming-infinite-retentive-llm","slug":"sirllm-streaming-infinite-retentive-llm","title":"SirLLM: Streaming Infinite Retentive LLM","date":"2024-05-21","arxiv_id":"2405.12528","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":1,"n_ran_checked":3,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sirllm-streaming-infinite-retentive-llm#ran","syntology_url":"https://syntology.ai/paper/2405.12528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12528"}},"official":{"repos":["zoeyyao27/sirllm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/prott3-protein-to-text-generation-for-text","slug":"prott3-protein-to-text-generation-for-text","title":"ProtT3: Protein-to-Text Generation for Text-based Protein Understanding","date":"2024-05-21","arxiv_id":"2405.12564","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/prott3-protein-to-text-generation-for-text#ran","syntology_url":"https://syntology.ai/paper/2405.12564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12564"}},"official":{"repos":["acharkq/prott3"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/unveiling-and-manipulating-prompt-influence","slug":"unveiling-and-manipulating-prompt-influence","title":"Unveiling and Manipulating Prompt Influence in Large Language Models","date":"2024-05-20","arxiv_id":"2405.11891","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unveiling-and-manipulating-prompt-influence#ran","syntology_url":"https://syntology.ai/paper/2405.11891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11891"}},"official":{"repos":["zijian678/tdd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/spor-a-comprehensive-and-practical-evaluation","slug":"spor-a-comprehensive-and-practical-evaluation","title":"SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation","date":"2024-05-17","arxiv_id":"2405.10650","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":1,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/spor-a-comprehensive-and-practical-evaluation#ran","syntology_url":"https://syntology.ai/paper/2405.10650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10650"}},"official":{"repos":["xzy-xzy/spor"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/explanation-as-a-watermark-towards-harmless","slug":"explanation-as-a-watermark-towards-harmless","title":"Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution","date":"2024-05-08","arxiv_id":"2405.04825","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/explanation-as-a-watermark-towards-harmless#ran","syntology_url":"https://syntology.ai/paper/2405.04825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04825"}},"official":{"repos":["shaoshuo-ss/eaaw"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/when-to-trust-llms-aligning-confidence-with","slug":"when-to-trust-llms-aligning-confidence-with","title":"When to Trust LLMs: Aligning Confidence with Response Quality","date":"2024-04-26","arxiv_id":"2404.17287","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/when-to-trust-llms-aligning-confidence-with#ran","syntology_url":"https://syntology.ai/paper/2404.17287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.17287"}},"official":{"repos":["taoshuchang/conqord"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/semantic-routing-for-enhanced-performance-of","slug":"semantic-routing-for-enhanced-performance-of","title":"Semantic Routing for Enhanced Performance of LLM-Assisted Intent-Based 5G Core Network Management and Orchestration","date":"2024-04-24","arxiv_id":"2404.15869","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semantic-routing-for-enhanced-performance-of#ran","syntology_url":"https://syntology.ai/paper/2404.15869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15869"}},"official":null}},{"url":"/paper/bridging-the-gap-between-different","slug":"bridging-the-gap-between-different","title":"Bridging the Gap between Different Vocabularies for LLM Ensemble","date":"2024-04-15","arxiv_id":"2404.09492","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bridging-the-gap-between-different#ran","syntology_url":"https://syntology.ai/paper/2404.09492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09492"}},"official":{"repos":["xydaytoy/eva"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/continuous-language-model-interpolation-for","slug":"continuous-language-model-interpolation-for","title":"Continuous Language Model Interpolation for Dynamic and Controllable Text Generation","date":"2024-04-10","arxiv_id":"2404.07117","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/continuous-language-model-interpolation-for#ran","syntology_url":"https://syntology.ai/paper/2404.07117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07117"}},"official":{"repos":["skangasl/continuous-lm-interpolation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-and-improving-compositional","slug":"benchmarking-and-improving-compositional","title":"Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation","date":"2024-04-05","arxiv_id":"2404.04232","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-and-improving-compositional#ran","syntology_url":"https://syntology.ai/paper/2404.04232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04232"}},"official":{"repos":["tqzhong/cg4mctg"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-in-language-models-assessment","slug":"uncertainty-in-language-models-assessment","title":"Uncertainty in Language Models: Assessment through Rank-Calibration","date":"2024-04-04","arxiv_id":"2404.03163","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uncertainty-in-language-models-assessment#ran","syntology_url":"https://syntology.ai/paper/2404.03163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03163"}},"official":{"repos":["shuoli90/rank-calibration"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/from-pixels-to-graphs-open-vocabulary-scene","slug":"from-pixels-to-graphs-open-vocabulary-scene","title":"From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models","date":"2024-04-01","arxiv_id":"2404.00906","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/from-pixels-to-graphs-open-vocabulary-scene#ran","syntology_url":"https://syntology.ai/paper/2404.00906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00906"}},"official":{"repos":["shtuplus/pix2grp_cvpr2024"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-by-correction-efficient-tuning-task","slug":"learning-by-correction-efficient-tuning-task","title":"Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning","date":"2024-04-01","arxiv_id":"2404.00909","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":1,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-by-correction-efficient-tuning-task#ran","syntology_url":"https://syntology.ai/paper/2404.00909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00909"}},"official":{"repos":["shtuplus/iccc_cvpr2024"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/developing-safe-and-responsible-large","slug":"developing-safe-and-responsible-large","title":"Developing Safe and Responsible Large Language Model : Can We Balance Bias Reduction and Language Understanding in Large Language Models?","date":"2024-04-01","arxiv_id":"2404.01399","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/developing-safe-and-responsible-large#ran","syntology_url":"https://syntology.ai/paper/2404.01399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01399"}},"official":{"repos":["shainarazavi/safe-responsible-llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/set-aligning-framework-for-auto-regressive","slug":"set-aligning-framework-for-auto-regressive","title":"Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation","date":"2024-04-01","arxiv_id":"2404.01532","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/set-aligning-framework-for-auto-regressive#ran","syntology_url":"https://syntology.ai/paper/2404.01532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01532"}},"official":{"repos":["xingwei-warwick/set-aligning-event-temporal-graph-generation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-impact-of-prompts-on-zero-shot-detection","slug":"the-impact-of-prompts-on-zero-shot-detection","title":"The Impact of Prompts on Zero-Shot Detection of AI-Generated Text","date":"2024-03-29","arxiv_id":"2403.20127","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-impact-of-prompts-on-zero-shot-detection#ran","syntology_url":"https://syntology.ai/paper/2403.20127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.20127"}},"official":{"repos":["kaito25atugich/detector"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/omniparser-a-unified-framework-for-text","slug":"omniparser-a-unified-framework-for-text","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","date":"2024-03-28","arxiv_id":"2403.19128","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/omniparser-a-unified-framework-for-text#ran","syntology_url":"https://syntology.ai/paper/2403.19128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19128"}},"official":{"repos":["alibabaresearch/advancedliteratemachinery"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhanced-generative-recommendation-via","slug":"enhanced-generative-recommendation-via","title":"Content-Based Collaborative Generation for Recommender Systems","date":"2024-03-27","arxiv_id":"2403.18480","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/enhanced-generative-recommendation-via#ran","syntology_url":"https://syntology.ai/paper/2403.18480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18480"}},"official":{"repos":["junewang0614/colarec"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-laws-for-dense-retrieval","slug":"scaling-laws-for-dense-retrieval","title":"Scaling Laws For Dense Retrieval","date":"2024-03-27","arxiv_id":"2403.18684","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scaling-laws-for-dense-retrieval#ran","syntology_url":"https://syntology.ai/paper/2403.18684","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18684"}},"official":{"repos":["jingtaozhan/drscale"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-llm-recsys-alignment-with-textual-id","slug":"towards-llm-recsys-alignment-with-textual-id","title":"IDGenRec: LLM-RecSys Alignment with Textual ID Learning","date":"2024-03-27","arxiv_id":"2403.19021","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-llm-recsys-alignment-with-textual-id#ran","syntology_url":"https://syntology.ai/paper/2403.19021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19021"}},"official":{"repos":["agiresearch/idgenrec"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lita-language-instructed-temporal","slug":"lita-language-instructed-temporal","title":"LITA: Language Instructed Temporal-Localization Assistant","date":"2024-03-27","arxiv_id":"2403.19046","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lita-language-instructed-temporal#ran","syntology_url":"https://syntology.ai/paper/2403.19046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19046"}},"official":{"repos":["nvlabs/lita"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/urbanvlp-a-multi-granularity-vision-language","slug":"urbanvlp-a-multi-granularity-vision-language","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","date":"2024-03-25","arxiv_id":"2403.16831","repositories_listed":2,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":3,"n_no_contract":8,"n_pointer_only":20,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 3 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/urbanvlp-a-multi-granularity-vision-language#ran","syntology_url":"https://syntology.ai/paper/2403.16831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16831"}},"official":{"repos":["citymind-lab/urbanvlp"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/attribute-first-then-generate-locally","slug":"attribute-first-then-generate-locally","title":"Attribute First, then Generate: Locally-attributable Grounded Text Generation","date":"2024-03-25","arxiv_id":"2403.17104","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/attribute-first-then-generate-locally#ran","syntology_url":"https://syntology.ai/paper/2403.17104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17104"}},"official":{"repos":["lovodkin93/attribute-first-then-generate"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llamafactory-unified-efficient-fine-tuning-of","slug":"llamafactory-unified-efficient-fine-tuning-of","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","date":"2024-03-20","arxiv_id":"2403.13372","repositories_listed":8,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/llamafactory-unified-efficient-fine-tuning-of#ran","syntology_url":"https://syntology.ai/paper/2403.13372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13372"}},"official":{"repos":["hiyouga/llama-factory"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/dynamic-reward-adjustment-in-multi-reward","slug":"dynamic-reward-adjustment-in-multi-reward","title":"Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation","date":"2024-03-20","arxiv_id":"2403.13578","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dynamic-reward-adjustment-in-multi-reward#ran","syntology_url":"https://syntology.ai/paper/2403.13578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13578"}},"official":{"repos":["michigannlp/dynaopt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/embedded-named-entity-recognition-using","slug":"embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/embedded-named-entity-recognition-using#ran","syntology_url":"https://syntology.ai/paper/2403.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11747"}},"official":{"repos":["nicpopovic/stoke","nicpopovic/ember"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dragin-dynamic-retrieval-augmented-generation","slug":"dragin-dynamic-retrieval-augmented-generation","title":"DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models","date":"2024-03-15","arxiv_id":"2403.10081","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dragin-dynamic-retrieval-augmented-generation#ran","syntology_url":"https://syntology.ai/paper/2403.10081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10081"}},"official":{"repos":["oneal2000/dragin"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dsp-dynamic-sequence-parallelism-for-multi","slug":"dsp-dynamic-sequence-parallelism-for-multi","title":"DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers","date":"2024-03-15","arxiv_id":"2403.10266","repositories_listed":2,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/dsp-dynamic-sequence-parallelism-for-multi#ran","syntology_url":"https://syntology.ai/paper/2403.10266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10266"}},"official":{"repos":["nus-hpc-ai-lab/opendit"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/keyformer-kv-cache-reduction-through-key","slug":"keyformer-kv-cache-reduction-through-key","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","date":"2024-03-14","arxiv_id":"2403.09054","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/keyformer-kv-cache-reduction-through-key#ran","syntology_url":"https://syntology.ai/paper/2403.09054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09054"}},"official":{"repos":["d-matrix-ai/keyformer-llm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-pretrained-structured-transformers","slug":"generative-pretrained-structured-transformers","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","date":"2024-03-13","arxiv_id":"2403.08293","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generative-pretrained-structured-transformers#ran","syntology_url":"https://syntology.ai/paper/2403.08293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08293"}},"official":{"repos":["ant-research/structuredlm_rtdt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/textual-knowledge-matters-cross-modality-co","slug":"textual-knowledge-matters-cross-modality-co","title":"Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery","date":"2024-03-12","arxiv_id":"2403.07369","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/textual-knowledge-matters-cross-modality-co#ran","syntology_url":"https://syntology.ai/paper/2403.07369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07369"}},"official":{"repos":["haiyangzheng/textgcd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/complex-reasoning-over-logical-queries-on","slug":"complex-reasoning-over-logical-queries-on","title":"Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs","date":"2024-03-12","arxiv_id":"2403.07398","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/complex-reasoning-over-logical-queries-on#ran","syntology_url":"https://syntology.ai/paper/2403.07398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07398"}},"official":{"repos":["tqfang/complex-commonsense-reasoning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/alarm-align-language-models-via-hierarchical","slug":"alarm-align-language-models-via-hierarchical","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling","date":"2024-03-11","arxiv_id":"2403.06754","repositories_listed":1,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/alarm-align-language-models-via-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2403.06754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06754"}},"official":{"repos":["halfrot/ALaRM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/calibrating-large-language-models-using-their","slug":"calibrating-large-language-models-using-their","title":"Calibrating Large Language Models Using Their Generations Only","date":"2024-03-09","arxiv_id":"2403.05973","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/calibrating-large-language-models-using-their#ran","syntology_url":"https://syntology.ai/paper/2403.05973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05973"}},"official":{"repos":["parameterlab/apricot"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/quantifying-contamination-in-evaluating-code","slug":"quantifying-contamination-in-evaluating-code","title":"Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models","date":"2024-03-06","arxiv_id":"2403.04811","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/quantifying-contamination-in-evaluating-code#ran","syntology_url":"https://syntology.ai/paper/2403.04811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04811"}},"official":{"repos":["yale-nlp/code-llm-contamination"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/halc-object-hallucination-reduction-via","slug":"halc-object-hallucination-reduction-via","title":"HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding","date":"2024-03-01","arxiv_id":"2403.00425","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/halc-object-hallucination-reduction-via#ran","syntology_url":"https://syntology.ai/paper/2403.00425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00425"}},"official":{"repos":["billchan226/halc","bradyfu/awesome-multimodal-large-language-models"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/the-all-seeing-project-v2-towards-general","slug":"the-all-seeing-project-v2-towards-general","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","date":"2024-02-29","arxiv_id":"2402.19474","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":2,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-all-seeing-project-v2-towards-general#ran","syntology_url":"https://syntology.ai/paper/2402.19474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19474"}},"official":{"repos":["opengvlab/all-seeing"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-multi-document-information","slug":"exploring-multi-document-information","title":"A Sentiment Consolidation Framework for Meta-Review Generation","date":"2024-02-28","arxiv_id":"2402.18005","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploring-multi-document-information#ran","syntology_url":"https://syntology.ai/paper/2402.18005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18005"}},"official":{"repos":["oaimli/metareviewinglogic"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-fact-assessing-multilingual-llms-multi","slug":"multi-fact-assessing-multilingual-llms-multi","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","date":"2024-02-28","arxiv_id":"2402.18045","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-fact-assessing-multilingual-llms-multi#ran","syntology_url":"https://syntology.ai/paper/2402.18045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18045"}},"official":{"repos":["sheikhshafayat/multi-fact"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-open-ended-text-generation-via","slug":"improving-open-ended-text-generation-via","title":"Improving Open-Ended Text Generation via Adaptive Decoding","date":"2024-02-28","arxiv_id":"2402.18223","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/improving-open-ended-text-generation-via#ran","syntology_url":"https://syntology.ai/paper/2402.18223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18223"}},"official":{"repos":["zwhong714/adaptive_decoding"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/simple-linear-attention-language-models","slug":"simple-linear-attention-language-models","title":"Simple linear attention language models balance the recall-throughput tradeoff","date":"2024-02-28","arxiv_id":"2402.18668","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simple-linear-attention-language-models#ran","syntology_url":"https://syntology.ai/paper/2402.18668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18668"}},"official":{"repos":["hazyresearch/based","hazyresearch/zoology"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/grounding-language-models-for-visual-entity","slug":"grounding-language-models-for-visual-entity","title":"Grounding Language Models for Visual Entity Recognition","date":"2024-02-28","arxiv_id":"2402.18695","repositories_listed":1,"syntology":{"n":26,"n_ran":12,"n_constructed":2,"n_ran_checked":7,"n_instrument":5,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/grounding-language-models-for-visual-entity#ran","syntology_url":"https://syntology.ai/paper/2402.18695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18695"}},"official":{"repos":["mrzilinxiao/autover"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":7,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-is-accurate-generation","slug":"retrieval-is-accurate-generation","title":"Retrieval is Accurate Generation","date":"2024-02-27","arxiv_id":"2402.17532","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/retrieval-is-accurate-generation#ran","syntology_url":"https://syntology.ai/paper/2402.17532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17532"}},"official":{"repos":["gmftbygmftby/copyisallyouneed"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["community","unlocated"]}}},{"url":"/paper/truthx-alleviating-hallucinations-by-editing","slug":"truthx-alleviating-hallucinations-by-editing","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","date":"2024-02-27","arxiv_id":"2402.17811","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/truthx-alleviating-hallucinations-by-editing#ran","syntology_url":"https://syntology.ai/paper/2402.17811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17811"}},"official":{"repos":["ictnlp/truthx"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/likelihood-based-mitigation-of-evaluation","slug":"likelihood-based-mitigation-of-evaluation","title":"Likelihood-based Mitigation of Evaluation Bias in Large Language Models","date":"2024-02-25","arxiv_id":"2402.15987","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/likelihood-based-mitigation-of-evaluation#ran","syntology_url":"https://syntology.ai/paper/2402.15987","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15987"}},"official":{"repos":["stjohn2007/likelihood_bias"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/chatmusician-understanding-and-generating","slug":"chatmusician-understanding-and-generating","title":"ChatMusician: Understanding and Generating Music Intrinsically with LLM","date":"2024-02-25","arxiv_id":"2402.16153","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/chatmusician-understanding-and-generating#ran","syntology_url":"https://syntology.ai/paper/2402.16153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16153"}},"official":{"repos":["hf-lin/ChatMusician"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/seeing-is-believing-mitigating-hallucination","slug":"seeing-is-believing-mitigating-hallucination","title":"Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding","date":"2024-02-23","arxiv_id":"2402.15300","repositories_listed":2,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":17,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/seeing-is-believing-mitigating-hallucination#ran","syntology_url":"https://syntology.ai/paper/2402.15300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15300"}},"official":{"repos":["d-ailin/clip-guided-decoding"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-generation-with-1","slug":"counterfactual-generation-with-1","title":"Counterfactual Generation with Identifiability Guarantees","date":"2024-02-23","arxiv_id":"2402.15309","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/counterfactual-generation-with-1#ran","syntology_url":"https://syntology.ai/paper/2402.15309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15309"}},"official":{"repos":["hanqi-qi/matte"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ouroboros-speculative-decoding-with-large","slug":"ouroboros-speculative-decoding-with-large","title":"Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding","date":"2024-02-21","arxiv_id":"2402.13720","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ouroboros-speculative-decoding-with-large#ran","syntology_url":"https://syntology.ai/paper/2402.13720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13720"}},"official":{"repos":["thunlp/ouroboros"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/the-finben-an-holistic-financial-benchmark","slug":"the-finben-an-holistic-financial-benchmark","title":"FinBen: A Holistic Financial Benchmark for Large Language Models","date":"2024-02-20","arxiv_id":"2402.12659","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/the-finben-an-holistic-financial-benchmark#ran","syntology_url":"https://syntology.ai/paper/2402.12659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12659"}},"official":{"repos":["the-finai/pixiu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"f81f7dd86349617efa3325f795430b4ed885b608b2a901989177ac4c49607444","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}