{"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/language-modeling/papers/19","list_of":"/task/language-modeling","task":"Language Modeling","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":19,"pages_in_order":142,"rows_per_page":100,"rows":[1801,1900],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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/language-modeling","prev":"/task/language-modeling/papers/18","next":"/task/language-modeling/papers/20","papers":[{"url":"/paper/cross-model-control-improving-multiple-large","slug":"cross-model-control-improving-multiple-large","title":"Cross-model Control: Improving Multiple Large Language Models in One-time Training","date":"2024-10-23","arxiv_id":"2410.17599","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cross-model-control-improving-multiple-large#ran","syntology_url":"https://syntology.ai/paper/2410.17599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17599"}},"official":{"repos":["wujwyi/cmc"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/generalizations-across-filler-gap","slug":"generalizations-across-filler-gap","title":"Generalizations across filler-gap dependencies in neural language models","date":"2024-10-23","arxiv_id":"2410.18225","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-diffusion-language-models-via","slug":"scaling-diffusion-language-models-via","title":"Scaling Diffusion Language Models via Adaptation from Autoregressive Models","date":"2024-10-23","arxiv_id":"2410.17891","repositories_listed":1,"syntology":{"n":22,"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":22,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/scaling-diffusion-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2410.17891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17891"}},"official":{"repos":["hkunlp/diffullama"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/adsorb-agent-autonomous-identification-of","slug":"adsorb-agent-autonomous-identification-of","title":"Adsorb-Agent: Autonomous Identification of Stable Adsorption Configurations via Large Language Model Agent","date":"2024-10-22","arxiv_id":"2410.16658","repositories_listed":1,"syntology":null},{"url":"/paper/automated-spinal-mri-labelling-from-reports","slug":"automated-spinal-mri-labelling-from-reports","title":"Automated Spinal MRI Labelling from Reports Using a Large Language Model","date":"2024-10-22","arxiv_id":"2410.17235","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-speech-tokenizer-in-text-to-speech","slug":"continuous-speech-tokenizer-in-text-to-speech","title":"Continuous Speech Tokenizer in Text To Speech","date":"2024-10-22","arxiv_id":"2410.17081","repositories_listed":1,"syntology":null},{"url":"/paper/dnahlm-dna-sequence-and-human-language-mixed","slug":"dnahlm-dna-sequence-and-human-language-mixed","title":"DNAHLM -- DNA sequence and Human Language mixed large language Model","date":"2024-10-22","arxiv_id":"2410.16917","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-possibilities-of-ai-powered-legal","slug":"exploring-possibilities-of-ai-powered-legal","title":"Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling","date":"2024-10-22","arxiv_id":"2410.17210","repositories_listed":1,"syntology":null},{"url":"/paper/frontiers-in-intelligent-colonoscopy","slug":"frontiers-in-intelligent-colonoscopy","title":"Frontiers in Intelligent Colonoscopy","date":"2024-10-22","arxiv_id":"2410.17241","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/frontiers-in-intelligent-colonoscopy#ran","syntology_url":"https://syntology.ai/paper/2410.17241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17241"}},"official":{"repos":["ai4colonoscopy/intelliscope"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/math-neurosurgery-isolating-language-models","slug":"math-neurosurgery-isolating-language-models","title":"Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes","date":"2024-10-22","arxiv_id":"2410.16930","repositories_listed":1,"syntology":null},{"url":"/paper/miniplm-knowledge-distillation-for-pre","slug":"miniplm-knowledge-distillation-for-pre","title":"MiniPLM: Knowledge Distillation for Pre-Training Language Models","date":"2024-10-22","arxiv_id":"2410.17215","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/miniplm-knowledge-distillation-for-pre#ran","syntology_url":"https://syntology.ai/paper/2410.17215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17215"}},"official":{"repos":["thu-coai/miniplm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/navigating-noisy-feedback-enhancing","slug":"navigating-noisy-feedback-enhancing","title":"Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models","date":"2024-10-22","arxiv_id":"2410.17389","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/navigating-noisy-feedback-enhancing#ran","syntology_url":"https://syntology.ai/paper/2410.17389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17389"}},"official":{"repos":["sy-shi/RLAIF_ScoreDiff"],"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"]}}},{"url":"/paper/satori-towards-proactive-ar-assistant-with","slug":"satori-towards-proactive-ar-assistant-with","title":"Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling","date":"2024-10-22","arxiv_id":"2410.16668","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-influence-and-fact-tracing-for-large","slug":"scalable-influence-and-fact-tracing-for-large","title":"Scalable Influence and Fact Tracing for Large Language Model Pretraining","date":"2024-10-22","arxiv_id":"2410.17413","repositories_listed":1,"syntology":null},{"url":"/paper/science-out-of-its-ivory-tower-improving","slug":"science-out-of-its-ivory-tower-improving","title":"Science Out of Its Ivory Tower: Improving Accessibility with Reinforcement Learning","date":"2024-10-22","arxiv_id":"2410.17088","repositories_listed":1,"syntology":null},{"url":"/paper/a-realistic-threat-model-for-large-language","slug":"a-realistic-threat-model-for-large-language","title":"A Realistic Threat Model for Large Language Model Jailbreaks","date":"2024-10-21","arxiv_id":"2410.16222","repositories_listed":1,"syntology":null},{"url":"/paper/autotrain-no-code-training-for-state-of-the","slug":"autotrain-no-code-training-for-state-of-the","title":"AutoTrain: No-code training for state-of-the-art models","date":"2024-10-21","arxiv_id":"2410.15735","repositories_listed":1,"syntology":null},{"url":"/paper/building-a-coding-assistant-via-the-retrieval","slug":"building-a-coding-assistant-via-the-retrieval","title":"Building A Coding Assistant via the Retrieval-Augmented Language Model","date":"2024-10-21","arxiv_id":"2410.16229","repositories_listed":1,"syntology":null},{"url":"/paper/cpe-pro-a-structure-sensitive-deep-learning","slug":"cpe-pro-a-structure-sensitive-deep-learning","title":"CPE-Pro: A Structure-Sensitive Deep Learning Method for Protein Representation and Origin Evaluation","date":"2024-10-21","arxiv_id":"2410.15592","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-and-data-augmentation-for","slug":"deep-learning-and-data-augmentation-for","title":"Deep Learning and Data Augmentation for Detecting Self-Admitted Technical Debt","date":"2024-10-21","arxiv_id":"2410.15804","repositories_listed":1,"syntology":null},{"url":"/paper/from-tokens-to-materials-leveraging-language","slug":"from-tokens-to-materials-leveraging-language","title":"From Tokens to Materials: Leveraging Language Models for Scientific Discovery","date":"2024-10-21","arxiv_id":"2410.16165","repositories_listed":1,"syntology":null},{"url":"/paper/katzbot-revolutionizing-academic-chatbot-for","slug":"katzbot-revolutionizing-academic-chatbot-for","title":"KatzBot: Revolutionizing Academic Chatbot for Enhanced Communication","date":"2024-10-21","arxiv_id":"2410.16385","repositories_listed":1,"syntology":null},{"url":"/paper/residual-vector-quantization-for-kv-cache","slug":"residual-vector-quantization-for-kv-cache","title":"Residual vector quantization for KV cache compression in large language model","date":"2024-10-21","arxiv_id":"2410.15704","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/residual-vector-quantization-for-kv-cache#ran","syntology_url":"https://syntology.ai/paper/2410.15704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15704"}},"official":{"repos":["iankur/vqllm"],"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/rm-bench-benchmarking-reward-models-of","slug":"rm-bench-benchmarking-reward-models-of","title":"RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style","date":"2024-10-21","arxiv_id":"2410.16184","repositories_listed":1,"syntology":null},{"url":"/paper/seislm-a-foundation-model-for-seismic","slug":"seislm-a-foundation-model-for-seismic","title":"SeisLM: a Foundation Model for Seismic Waveforms","date":"2024-10-21","arxiv_id":"2410.15765","repositories_listed":1,"syntology":null},{"url":"/paper/the-effect-of-fine-tuning-on-language-model","slug":"the-effect-of-fine-tuning-on-language-model","title":"The effect of fine-tuning on language model toxicity","date":"2024-10-21","arxiv_id":"2410.15821","repositories_listed":1,"syntology":null},{"url":"/paper/berttime-stories-investigating-the-role-of","slug":"berttime-stories-investigating-the-role-of","title":"BERTtime Stories: Investigating the Role of Synthetic Story Data in Language pre-training","date":"2024-10-20","arxiv_id":"2410.15365","repositories_listed":1,"syntology":null},{"url":"/paper/dna-language-model-and-interpretable-graph","slug":"dna-language-model-and-interpretable-graph","title":"DNA Language Model and Interpretable Graph Neural Network Identify Genes and Pathways Involved in Rare Diseases","date":"2024-10-20","arxiv_id":"2410.15367","repositories_listed":1,"syntology":null},{"url":"/paper/less-is-more-parameter-efficient-selection-of","slug":"less-is-more-parameter-efficient-selection-of","title":"Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning","date":"2024-10-19","arxiv_id":"2410.15148","repositories_listed":1,"syntology":null},{"url":"/paper/melt-materials-aware-continued-pre-training","slug":"melt-materials-aware-continued-pre-training","title":"MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science","date":"2024-10-19","arxiv_id":"2410.15126","repositories_listed":1,"syntology":null},{"url":"/paper/a-systematic-study-of-cross-layer-kv-sharing","slug":"a-systematic-study-of-cross-layer-kv-sharing","title":"A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference","date":"2024-10-18","arxiv_id":"2410.14442","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"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) · 2 unverified","sample_list":"/paper/a-systematic-study-of-cross-layer-kv-sharing#ran","syntology_url":"https://syntology.ai/paper/2410.14442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14442"}},"official":{"repos":["whyNLP/LCKV"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/momentumsmoe-integrating-momentum-into-sparse","slug":"momentumsmoe-integrating-momentum-into-sparse","title":"MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts","date":"2024-10-18","arxiv_id":"2410.14574","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/momentumsmoe-integrating-momentum-into-sparse#ran","syntology_url":"https://syntology.ai/paper/2410.14574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14574"}},"official":{"repos":["rachtsy/momentumsmoe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/montessori-instruct-generate-influential","slug":"montessori-instruct-generate-influential","title":"Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning","date":"2024-10-18","arxiv_id":"2410.14208","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/montessori-instruct-generate-influential#ran","syntology_url":"https://syntology.ai/paper/2410.14208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14208"}},"official":{"repos":["cxcscmu/montessori-instruct"],"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/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"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) · 3 unverified","sample_list":"/paper/paths-over-graph-knowledge-graph-enpowered#ran","syntology_url":"https://syntology.ai/paper/2410.14211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14211"}},"official":null}},{"url":"/paper/snac-multi-scale-neural-audio-codec","slug":"snac-multi-scale-neural-audio-codec","title":"SNAC: Multi-Scale Neural Audio Codec","date":"2024-10-18","arxiv_id":"2410.14411","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":0,"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/snac-multi-scale-neural-audio-codec#ran","syntology_url":"https://syntology.ai/paper/2410.14411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14411"}},"official":{"repos":["hubertsiuzdak/snac"],"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/sprig-improving-large-language-model","slug":"sprig-improving-large-language-model","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","date":"2024-10-18","arxiv_id":"2410.14826","repositories_listed":1,"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sprig-improving-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.14826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14826"}},"official":{"repos":["orange0629/prompting"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/tell-me-what-i-need-to-know-exploring-llm","slug":"tell-me-what-i-need-to-know-exploring-llm","title":"Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization","date":"2024-10-18","arxiv_id":"2410.14545","repositories_listed":1,"syntology":null},{"url":"/paper/unlearning-backdoor-attacks-for-llms-with","slug":"unlearning-backdoor-attacks-for-llms-with","title":"Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation","date":"2024-10-18","arxiv_id":"2410.14425","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/unlearning-backdoor-attacks-for-llms-with#ran","syntology_url":"https://syntology.ai/paper/2410.14425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14425"}},"official":{"repos":["shuaizhao95/Unlearning"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/a-common-pitfall-of-margin-based-language","slug":"a-common-pitfall-of-margin-based-language","title":"A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement","date":"2024-10-17","arxiv_id":"2410.13828","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":5,"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/a-common-pitfall-of-margin-based-language#ran","syntology_url":"https://syntology.ai/paper/2410.13828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13828"}},"official":{"repos":["humainlab/understand_marginpo"],"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/aixcoder-7b-a-lightweight-and-effective-large","slug":"aixcoder-7b-a-lightweight-and-effective-large","title":"aiXcoder-7B: A Lightweight and Effective Large Language Model for Code Processing","date":"2024-10-17","arxiv_id":"2410.13187","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/aixcoder-7b-a-lightweight-and-effective-large#ran","syntology_url":"https://syntology.ai/paper/2410.13187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13187"}},"official":{"repos":["aixcoder-plugin/aixcoder-7b"],"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/detecting-ai-generated-texts-in-cross-domains","slug":"detecting-ai-generated-texts-in-cross-domains","title":"Detecting AI-Generated Texts in Cross-Domains","date":"2024-10-17","arxiv_id":"2410.13966","repositories_listed":1,"syntology":null},{"url":"/paper/dplm-2-a-multimodal-diffusion-protein","slug":"dplm-2-a-multimodal-diffusion-protein","title":"DPLM-2: A Multimodal Diffusion Protein Language Model","date":"2024-10-17","arxiv_id":"2410.13782","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dplm-2-a-multimodal-diffusion-protein#ran","syntology_url":"https://syntology.ai/paper/2410.13782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13782"}},"official":null}},{"url":"/paper/exploring-the-design-space-of-visual-context","slug":"exploring-the-design-space-of-visual-context","title":"Exploring the Design Space of Visual Context Representation in Video MLLMs","date":"2024-10-17","arxiv_id":"2410.13694","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/exploring-the-design-space-of-visual-context#ran","syntology_url":"https://syntology.ai/paper/2410.13694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13694"}},"official":{"repos":["rucaibox/opt-visor"],"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/fire-fact-checking-with-iterative-retrieval","slug":"fire-fact-checking-with-iterative-retrieval","title":"FIRE: Fact-checking with Iterative Retrieval and Verification","date":"2024-10-17","arxiv_id":"2411.00784","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/fire-fact-checking-with-iterative-retrieval#ran","syntology_url":"https://syntology.ai/paper/2411.00784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00784"}},"official":{"repos":["mbzuai-nlp/fire"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/help-me-identify-is-an-llm-vqa-system-all-we","slug":"help-me-identify-is-an-llm-vqa-system-all-we","title":"Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?","date":"2024-10-17","arxiv_id":"2410.13651","repositories_listed":1,"syntology":null},{"url":"/paper/mapping-bias-in-vision-language-models","slug":"mapping-bias-in-vision-language-models","title":"debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias","date":"2024-10-17","arxiv_id":"2410.13146","repositories_listed":1,"syntology":null},{"url":"/paper/medinst-meta-dataset-of-biomedical","slug":"medinst-meta-dataset-of-biomedical","title":"MedINST: Meta Dataset of Biomedical Instructions","date":"2024-10-17","arxiv_id":"2410.13458","repositories_listed":1,"syntology":null},{"url":"/paper/mirage-bench-automatic-multilingual-benchmark","slug":"mirage-bench-automatic-multilingual-benchmark","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","date":"2024-10-17","arxiv_id":"2410.13716","repositories_listed":1,"syntology":null},{"url":"/paper/moba-a-two-level-agent-system-for-efficient","slug":"moba-a-two-level-agent-system-for-efficient","title":"MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation","date":"2024-10-17","arxiv_id":"2410.13757","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-role-of-attention-heads-in-large","slug":"on-the-role-of-attention-heads-in-large","title":"On the Role of Attention Heads in Large Language Model Safety","date":"2024-10-17","arxiv_id":"2410.13708","repositories_listed":1,"syntology":{"n":24,"n_ran":16,"n_constructed":0,"n_ran_checked":8,"n_instrument":8,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":24,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/on-the-role-of-attention-heads-in-large#ran","syntology_url":"https://syntology.ai/paper/2410.13708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13708"}},"official":{"repos":["ydyjya/safetyheadattribution"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/reproducibility-study-of-lico-explainable","slug":"reproducibility-study-of-lico-explainable","title":"Reproducibility study of \"LICO: Explainable Models with Language-Image Consistency\"","date":"2024-10-17","arxiv_id":"2410.13989","repositories_listed":1,"syntology":null},{"url":"/paper/sbi-rag-enhancing-math-word-problem-solving","slug":"sbi-rag-enhancing-math-word-problem-solving","title":"SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation","date":"2024-10-17","arxiv_id":"2410.13293","repositories_listed":1,"syntology":null},{"url":"/paper/cream-consistency-regularized-self-rewarding","slug":"cream-consistency-regularized-self-rewarding","title":"CREAM: Consistency Regularized Self-Rewarding Language Models","date":"2024-10-16","arxiv_id":"2410.12735","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"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) · 2 unverified","sample_list":"/paper/cream-consistency-regularized-self-rewarding#ran","syntology_url":"https://syntology.ai/paper/2410.12735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12735"}},"official":{"repos":["raibows/cream"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hero-at-averitec-the-herd-of-open-large","slug":"hero-at-averitec-the-herd-of-open-large","title":"HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World Claims","date":"2024-10-16","arxiv_id":"2410.12377","repositories_listed":1,"syntology":null},{"url":"/paper/preflexor-preference-based-recursive-language","slug":"preflexor-preference-based-recursive-language","title":"PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking","date":"2024-10-16","arxiv_id":"2410.12375","repositories_listed":1,"syntology":null},{"url":"/paper/reverse-engineering-the-reader","slug":"reverse-engineering-the-reader","title":"Reverse-Engineering the Reader","date":"2024-10-16","arxiv_id":"2410.13086","repositories_listed":1,"syntology":null},{"url":"/paper/sarcasm-detection-in-a-less-resourced","slug":"sarcasm-detection-in-a-less-resourced","title":"Sarcasm Detection in a Less-Resourced Language","date":"2024-10-16","arxiv_id":"2410.12704","repositories_listed":1,"syntology":null},{"url":"/paper/vividmed-vision-language-model-with-versatile","slug":"vividmed-vision-language-model-with-versatile","title":"VividMed: Vision Language Model with Versatile Visual Grounding for Medicine","date":"2024-10-16","arxiv_id":"2410.12694","repositories_listed":1,"syntology":null},{"url":"/paper/a-framework-for-adapting-human-robot","slug":"a-framework-for-adapting-human-robot","title":"A Framework for Adapting Human-Robot Interaction to Diverse User Groups","date":"2024-10-15","arxiv_id":"2410.11377","repositories_listed":1,"syntology":null},{"url":"/paper/de-jargonizing-science-for-journalists-with","slug":"de-jargonizing-science-for-journalists-with","title":"De-jargonizing Science for Journalists with GPT-4: A Pilot Study","date":"2024-10-15","arxiv_id":"2410.12069","repositories_listed":1,"syntology":null},{"url":"/paper/disp-llm-dimension-independent-structural","slug":"disp-llm-dimension-independent-structural","title":"DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models","date":"2024-10-15","arxiv_id":"2410.11988","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/disp-llm-dimension-independent-structural#ran","syntology_url":"https://syntology.ai/paper/2410.11988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11988"}},"official":{"repos":["ZhengaoLi/DISP-LLM-Dimension-Independent-Structural-Pruning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/fveval-understanding-language-model","slug":"fveval-understanding-language-model","title":"FVEval: Understanding Language Model Capabilities in Formal Verification of Digital Hardware","date":"2024-10-15","arxiv_id":"2410.23299","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-llm-embeddings-for-cross-dataset","slug":"leveraging-llm-embeddings-for-cross-dataset","title":"Leveraging LLM Embeddings for Cross Dataset Label Alignment and Zero Shot Music Emotion Prediction","date":"2024-10-15","arxiv_id":"2410.11522","repositories_listed":1,"syntology":null},{"url":"/paper/mllm-can-see-dynamic-correction-decoding-for","slug":"mllm-can-see-dynamic-correction-decoding-for","title":"MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation","date":"2024-10-15","arxiv_id":"2410.11779","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/mllm-can-see-dynamic-correction-decoding-for#ran","syntology_url":"https://syntology.ai/paper/2410.11779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11779"}},"official":{"repos":["zjunlp/Deco"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/process-reward-model-with-q-value-rankings","slug":"process-reward-model-with-q-value-rankings","title":"Process Reward Model with Q-Value Rankings","date":"2024-10-15","arxiv_id":"2410.11287","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/process-reward-model-with-q-value-rankings#ran","syntology_url":"https://syntology.ai/paper/2410.11287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11287"}},"official":{"repos":["WindyLee0822/Process_Q_Model"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rate-score-reward-models-with-imperfect","slug":"rate-score-reward-models-with-imperfect","title":"RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals","date":"2024-10-15","arxiv_id":"2410.11348","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"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) · 1 unverified","sample_list":"/paper/rate-score-reward-models-with-imperfect#ran","syntology_url":"https://syntology.ai/paper/2410.11348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11348"}},"official":{"repos":["toddnief/rate"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/search-engines-in-an-ai-era-the-false-promise","slug":"search-engines-in-an-ai-era-the-false-promise","title":"Search Engines in an AI Era: The False Promise of Factual and Verifiable Source-Cited Responses","date":"2024-10-15","arxiv_id":"2410.22349","repositories_listed":1,"syntology":null},{"url":"/paper/topolm-brain-like-spatio-functional","slug":"topolm-brain-like-spatio-functional","title":"TopoLM: brain-like spatio-functional organization in a topographic language model","date":"2024-10-15","arxiv_id":"2410.11516","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/topolm-brain-like-spatio-functional#ran","syntology_url":"https://syntology.ai/paper/2410.11516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11516"}},"official":{"repos":["epflneuroailab/topolm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/weatherdg-llm-assisted-procedural-weather","slug":"weatherdg-llm-assisted-procedural-weather","title":"WeatherDG: LLM-assisted Diffusion Model for Procedural Weather Generation in Domain-Generalized Semantic Segmentation","date":"2024-10-15","arxiv_id":"2410.12075","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-baseline-for-predicting-events-with","slug":"a-simple-baseline-for-predicting-events-with","title":"A Simple Baseline for Predicting Events with Auto-Regressive Tabular Transformers","date":"2024-10-14","arxiv_id":"2410.10648","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-the-esm2-protein-language-model","slug":"fine-tuning-the-esm2-protein-language-model","title":"Fine-tuning the ESM2 protein language model to understand the functional impact of missense variants","date":"2024-10-14","arxiv_id":"2410.10919","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-leverage-demonstration-data-in","slug":"how-to-leverage-demonstration-data-in","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","date":"2024-10-14","arxiv_id":"2410.10093","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/how-to-leverage-demonstration-data-in#ran","syntology_url":"https://syntology.ai/paper/2410.10093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10093"}},"official":{"repos":["tengxiao1/gsil"],"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/kblam-knowledge-base-augmented-language-model","slug":"kblam-knowledge-base-augmented-language-model","title":"KBLaM: Knowledge Base augmented Language Model","date":"2024-10-14","arxiv_id":"2410.10450","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/kblam-knowledge-base-augmented-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.10450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10450"}},"official":{"repos":["microsoft/KBLaM"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/language-model-preference-evaluation-with","slug":"language-model-preference-evaluation-with","title":"Language Model Preference Evaluation with Multiple Weak Evaluators","date":"2024-10-14","arxiv_id":"2410.12869","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"6 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/language-model-preference-evaluation-with#ran","syntology_url":"https://syntology.ai/paper/2410.12869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12869"}},"official":{"repos":["ppsmk388/GED"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-evaluation-via-matrix-1","slug":"large-language-model-evaluation-via-matrix-1","title":"Large Language Model Evaluation via Matrix Nuclear-Norm","date":"2024-10-14","arxiv_id":"2410.10672","repositories_listed":1,"syntology":null},{"url":"/paper/local-and-global-decoding-in-text-generation","slug":"local-and-global-decoding-in-text-generation","title":"Local and Global Decoding in Text Generation","date":"2024-10-14","arxiv_id":"2410.10810","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/local-and-global-decoding-in-text-generation#ran","syntology_url":"https://syntology.ai/paper/2410.10810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10810"}},"official":{"repos":["lowlypalace/global-decoding"],"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/predicting-from-strings-language-model","slug":"predicting-from-strings-language-model","title":"Predicting from Strings: Language Model Embeddings for Bayesian Optimization","date":"2024-10-14","arxiv_id":"2410.10190","repositories_listed":1,"syntology":null},{"url":"/paper/easyjudge-an-easy-to-use-tool-for","slug":"easyjudge-an-easy-to-use-tool-for","title":"EasyJudge: an Easy-to-use Tool for Comprehensive Response Evaluation of LLMs","date":"2024-10-13","arxiv_id":"2410.09775","repositories_listed":1,"syntology":null},{"url":"/paper/hardmath-a-benchmark-dataset-for-challenging","slug":"hardmath-a-benchmark-dataset-for-challenging","title":"HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics","date":"2024-10-13","arxiv_id":"2410.09988","repositories_listed":1,"syntology":null},{"url":"/paper/coral-order-agnostic-language-modeling-for","slug":"coral-order-agnostic-language-modeling-for","title":"COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement","date":"2024-10-12","arxiv_id":"2410.09675","repositories_listed":1,"syntology":null},{"url":"/paper/linked-eliciting-filtering-and-integrating","slug":"linked-eliciting-filtering-and-integrating","title":"LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning","date":"2024-10-12","arxiv_id":"2410.09541","repositories_listed":1,"syntology":null},{"url":"/paper/can-a-large-language-model-be-a-gaslighter","slug":"can-a-large-language-model-be-a-gaslighter","title":"Can a large language model be a gaslighter?","date":"2024-10-11","arxiv_id":"2410.09181","repositories_listed":1,"syntology":null},{"url":"/paper/distributionally-robust-self-supervised","slug":"distributionally-robust-self-supervised","title":"Distributionally robust self-supervised learning for tabular data","date":"2024-10-11","arxiv_id":"2410.08511","repositories_listed":1,"syntology":null},{"url":"/paper/do-unlearning-methods-remove-information-from","slug":"do-unlearning-methods-remove-information-from","title":"Do Unlearning Methods Remove Information from Language Model Weights?","date":"2024-10-11","arxiv_id":"2410.08827","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":1,"n_instrument":8,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"phrase":"9 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; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/do-unlearning-methods-remove-information-from#ran","syntology_url":"https://syntology.ai/paper/2410.08827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08827"}},"official":{"repos":["aghyad-deeb/unlearning_evaluation"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enterprise-benchmarks-for-large-language","slug":"enterprise-benchmarks-for-large-language","title":"Enterprise Benchmarks for Large Language Model Evaluation","date":"2024-10-11","arxiv_id":"2410.12857","repositories_listed":1,"syntology":null},{"url":"/paper/generation-with-dynamic-vocabulary","slug":"generation-with-dynamic-vocabulary","title":"Generation with Dynamic Vocabulary","date":"2024-10-11","arxiv_id":"2410.08481","repositories_listed":1,"syntology":null},{"url":"/paper/medmobile-a-mobile-sized-language-model-with","slug":"medmobile-a-mobile-sized-language-model-with","title":"MedMobile: A mobile-sized language model with expert-level clinical capabilities","date":"2024-10-11","arxiv_id":"2410.09019","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-fine-tuning-of-state","slug":"parameter-efficient-fine-tuning-of-state","title":"Parameter-Efficient Fine-Tuning of State Space Models","date":"2024-10-11","arxiv_id":"2410.09016","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":3,"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/parameter-efficient-fine-tuning-of-state#ran","syntology_url":"https://syntology.ai/paper/2410.09016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09016"}},"official":{"repos":["furiosa-ai/ssm-peft"],"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/pear-a-robust-and-flexible-automation","slug":"pear-a-robust-and-flexible-automation","title":"PEAR: A Robust and Flexible Automation Framework for Ptychography Enabled by Multiple Large Language Model Agents","date":"2024-10-11","arxiv_id":"2410.09034","repositories_listed":1,"syntology":null},{"url":"/paper/poisonbench-assessing-large-language-model","slug":"poisonbench-assessing-large-language-model","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","date":"2024-10-11","arxiv_id":"2410.08811","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/poisonbench-assessing-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.08811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08811"}},"official":{"repos":["tingchenfu/poisonbench"],"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/retraining-free-merging-of-sparse-mixture-of","slug":"retraining-free-merging-of-sparse-mixture-of","title":"Retraining-Free Merging of Sparse MoE via Hierarchical Clustering","date":"2024-10-11","arxiv_id":"2410.08589","repositories_listed":1,"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":8,"n_instrument":7,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"15 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; 7 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/retraining-free-merging-of-sparse-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2410.08589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08589"}},"official":{"repos":["wazenmai/hc-smoe"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/socialgaze-improving-the-integration-of-human","slug":"socialgaze-improving-the-integration-of-human","title":"SocialGaze: Improving the Integration of Human Social Norms in Large Language Models","date":"2024-10-11","arxiv_id":"2410.08698","repositories_listed":1,"syntology":null},{"url":"/paper/subzero-random-subspace-zeroth-order","slug":"subzero-random-subspace-zeroth-order","title":"Zeroth-Order Fine-Tuning of LLMs in Random Subspaces","date":"2024-10-11","arxiv_id":"2410.08989","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":15,"phrase":"11 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/subzero-random-subspace-zeroth-order#ran","syntology_url":"https://syntology.ai/paper/2410.08989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08989"}},"official":{"repos":["zimingyy/subzero"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/agrogpt-efficient-agricultural-vision","slug":"agrogpt-efficient-agricultural-vision","title":"AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuning","date":"2024-10-10","arxiv_id":"2410.08405","repositories_listed":1,"syntology":null},{"url":"/paper/bilinear-mlps-enable-weight-based-mechanistic","slug":"bilinear-mlps-enable-weight-based-mechanistic","title":"Bilinear MLPs enable weight-based mechanistic interpretability","date":"2024-10-10","arxiv_id":"2410.08417","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bilinear-mlps-enable-weight-based-mechanistic#ran","syntology_url":"https://syntology.ai/paper/2410.08417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08417"}},"official":{"repos":["tdooms/bilinear-decomposition"],"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/closing-the-loop-learning-to-generate-writing","slug":"closing-the-loop-learning-to-generate-writing","title":"Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions","date":"2024-10-10","arxiv_id":"2410.08058","repositories_listed":1,"syntology":null},{"url":"/paper/efficiently-learning-at-test-time-active-fine","slug":"efficiently-learning-at-test-time-active-fine","title":"Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs","date":"2024-10-10","arxiv_id":"2410.08020","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/efficiently-learning-at-test-time-active-fine#ran","syntology_url":"https://syntology.ai/paper/2410.08020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08020"}},"official":{"repos":["jonhue/activeft"],"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/hlm-cite-hybrid-language-model-workflow-for","slug":"hlm-cite-hybrid-language-model-workflow-for","title":"HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction","date":"2024-10-10","arxiv_id":"2410.09112","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/hlm-cite-hybrid-language-model-workflow-for#ran","syntology_url":"https://syntology.ai/paper/2410.09112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09112"}},"official":{"repos":["tsinghua-fib-lab/H-LM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/more-experts-than-galaxies-conditionally","slug":"more-experts-than-galaxies-conditionally","title":"More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing","date":"2024-10-10","arxiv_id":"2410.08003","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/more-experts-than-galaxies-conditionally#ran","syntology_url":"https://syntology.ai/paper/2410.08003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08003"}},"official":{"repos":["shaier/comet"],"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/multi-agent-collaborative-data-selection-for","slug":"multi-agent-collaborative-data-selection-for","title":"Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining","date":"2024-10-10","arxiv_id":"2410.08102","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":2,"n_no_contract":9,"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, 2 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-agent-collaborative-data-selection-for#ran","syntology_url":"https://syntology.ai/paper/2410.08102","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08102"}},"official":{"repos":["beccabai/multi-agent-data-selection"],"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"]}}}],"record_sha256":"810eae6e7333ce3b7e45756d3bacc8a21c23aa35763cdb66943320ac690d2198","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}