{"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-modelling/papers/29","list_of":"/task/language-modelling","task":"Language Modelling","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":29,"pages_in_order":177,"rows_per_page":100,"rows":[2801,2900],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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-modelling","prev":"/task/language-modelling/papers/28","next":"/task/language-modelling/papers/30","papers":[{"url":"/paper/low-redundant-optimization-for-large-language","slug":"low-redundant-optimization-for-large-language","title":"Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment","date":"2024-06-18","arxiv_id":"2406.12606","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":2,"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/low-redundant-optimization-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.12606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12606"}},"official":{"repos":["rucaibox/allo"],"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/magic-generating-self-correction-guideline","slug":"magic-generating-self-correction-guideline","title":"MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL","date":"2024-06-18","arxiv_id":"2406.12692","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":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) · 0 unverified","sample_list":"/paper/magic-generating-self-correction-guideline#ran","syntology_url":"https://syntology.ai/paper/2406.12692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12692"}},"official":{"repos":["microsoft/synqo"],"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/maskpure-improving-defense-against-text","slug":"maskpure-improving-defense-against-text","title":"MaskPure: Improving Defense Against Text Adversaries with Stochastic Purification","date":"2024-06-18","arxiv_id":"2406.13066","repositories_listed":1,"syntology":null},{"url":"/paper/moleculargpt-open-large-language-model-llm","slug":"moleculargpt-open-large-language-model-llm","title":"MolecularGPT: Open Large Language Model (LLM) for Few-Shot Molecular Property Prediction","date":"2024-06-18","arxiv_id":"2406.12950","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/moleculargpt-open-large-language-model-llm#ran","syntology_url":"https://syntology.ai/paper/2406.12950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12950"}},"official":{"repos":["nyushcs/moleculargpt"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/problem-solving-in-language-model-networks","slug":"problem-solving-in-language-model-networks","title":"Problem-Solving in Language Model Networks","date":"2024-06-18","arxiv_id":"2406.12374","repositories_listed":1,"syntology":null},{"url":"/paper/pslm-parallel-generation-of-text-and-speech","slug":"pslm-parallel-generation-of-text-and-speech","title":"PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems","date":"2024-06-18","arxiv_id":"2406.12428","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":5,"phrase":"6 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pslm-parallel-generation-of-text-and-speech#ran","syntology_url":"https://syntology.ai/paper/2406.12428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12428"}},"official":{"repos":["eleutherai/gpt-neox"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/queerbench-quantifying-discrimination-in","slug":"queerbench-quantifying-discrimination-in","title":"QueerBench: Quantifying Discrimination in Language Models Toward Queer Identities","date":"2024-06-18","arxiv_id":"2406.12399","repositories_listed":1,"syntology":null},{"url":"/paper/rs-gpt4v-a-unified-multimodal-instruction","slug":"rs-gpt4v-a-unified-multimodal-instruction","title":"RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image Understanding","date":"2024-06-18","arxiv_id":"2406.12479","repositories_listed":1,"syntology":null},{"url":"/paper/stealth-edits-for-provably-fixing-or","slug":"stealth-edits-for-provably-fixing-or","title":"Stealth edits to large language models","date":"2024-06-18","arxiv_id":"2406.12670","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-style-augmentation-via-large","slug":"adversarial-style-augmentation-via-large","title":"Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection","date":"2024-06-17","arxiv_id":"2406.11260","repositories_listed":1,"syntology":null},{"url":"/paper/avatar-optimizing-llm-agents-for-tool","slug":"avatar-optimizing-llm-agents-for-tool","title":"AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning","date":"2024-06-17","arxiv_id":"2406.11200","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/avatar-optimizing-llm-agents-for-tool#ran","syntology_url":"https://syntology.ai/paper/2406.11200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11200"}},"official":{"repos":["zou-group/avatar"],"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/citrus-chunked-instruction-aware-state","slug":"citrus-chunked-instruction-aware-state","title":"CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling","date":"2024-06-17","arxiv_id":"2406.12018","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":10,"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) · 5 unverified","sample_list":"/paper/citrus-chunked-instruction-aware-state#ran","syntology_url":"https://syntology.ai/paper/2406.12018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12018"}},"official":{"repos":["ybai-nlp/CItruS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/cosqa-enhancing-code-search-dataset-with","slug":"cosqa-enhancing-code-search-dataset-with","title":"CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents","date":"2024-06-17","arxiv_id":"2406.11589","repositories_listed":1,"syntology":null},{"url":"/paper/csrt-evaluation-and-analysis-of-llms-using","slug":"csrt-evaluation-and-analysis-of-llms-using","title":"Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding","date":"2024-06-17","arxiv_id":"2406.15481","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/csrt-evaluation-and-analysis-of-llms-using#ran","syntology_url":"https://syntology.ai/paper/2406.15481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15481"}},"official":{"repos":["haneul-yoo/csrt"],"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/deepseek-coder-v2-breaking-the-barrier-of","slug":"deepseek-coder-v2-breaking-the-barrier-of","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","date":"2024-06-17","arxiv_id":"2406.11931","repositories_listed":1,"syntology":null},{"url":"/paper/dialogue-action-tokens-steering-language","slug":"dialogue-action-tokens-steering-language","title":"Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner","date":"2024-06-17","arxiv_id":"2406.11978","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/dialogue-action-tokens-steering-language#ran","syntology_url":"https://syntology.ai/paper/2406.11978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11978"}},"official":{"repos":["likenneth/dialogue_action_token"],"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/fintruthqa-a-benchmark-dataset-for-evaluating","slug":"fintruthqa-a-benchmark-dataset-for-evaluating","title":"FinTruthQA: A Benchmark Dataset for Evaluating the Quality of Financial Information Disclosure","date":"2024-06-17","arxiv_id":"2406.12009","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":0,"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/fintruthqa-a-benchmark-dataset-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2406.12009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12009"}},"official":{"repos":["bethxx99/FinTruthQA"],"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/generative-visual-instruction-tuning","slug":"generative-visual-instruction-tuning","title":"Generative Visual Instruction Tuning","date":"2024-06-17","arxiv_id":"2406.11262","repositories_listed":1,"syntology":null},{"url":"/paper/global-data-constraints-ethical-and","slug":"global-data-constraints-ethical-and","title":"Problematic Tokens: Tokenizer Bias in Large Language Models","date":"2024-06-17","arxiv_id":"2406.11214","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-to-jailbreak-one-knowledge-point","slug":"knowledge-to-jailbreak-one-knowledge-point","title":"Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models","date":"2024-06-17","arxiv_id":"2406.11682","repositories_listed":1,"syntology":null},{"url":"/paper/language-modeling-with-editable-external","slug":"language-modeling-with-editable-external","title":"Language Modeling with Editable External Knowledge","date":"2024-06-17","arxiv_id":"2406.11830","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/language-modeling-with-editable-external#ran","syntology_url":"https://syntology.ai/paper/2406.11830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11830"}},"official":{"repos":["belindal/erase"],"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/mdpo-conditional-preference-optimization-for","slug":"mdpo-conditional-preference-optimization-for","title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models","date":"2024-06-17","arxiv_id":"2406.11839","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mdpo-conditional-preference-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2406.11839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11839"}},"official":{"repos":["luka-group/mDPO"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mmneuron-discovering-neuron-level-domain","slug":"mmneuron-discovering-neuron-level-domain","title":"MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model","date":"2024-06-17","arxiv_id":"2406.11193","repositories_listed":1,"syntology":null},{"url":"/paper/prefixing-attention-sinks-can-mitigate","slug":"prefixing-attention-sinks-can-mitigate","title":"Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization","date":"2024-06-17","arxiv_id":"2406.12016","repositories_listed":1,"syntology":null},{"url":"/paper/reframing-linguistic-bootstrapping-as-joint","slug":"reframing-linguistic-bootstrapping-as-joint","title":"Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models","date":"2024-06-17","arxiv_id":"2406.11977","repositories_listed":1,"syntology":null},{"url":"/paper/repliqa-a-question-answering-dataset-for","slug":"repliqa-a-question-answering-dataset-for","title":"RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content","date":"2024-06-17","arxiv_id":"2406.11811","repositories_listed":1,"syntology":null},{"url":"/paper/self-train-before-you-transcribe","slug":"self-train-before-you-transcribe","title":"Self-Train Before You Transcribe","date":"2024-06-17","arxiv_id":"2406.12937","repositories_listed":1,"syntology":null},{"url":"/paper/self-training-large-language-models-through","slug":"self-training-large-language-models-through","title":"Self-training Large Language Models through Knowledge Detection","date":"2024-06-17","arxiv_id":"2406.11275","repositories_listed":1,"syntology":null},{"url":"/paper/spa-vl-a-comprehensive-safety-preference","slug":"spa-vl-a-comprehensive-safety-preference","title":"SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model","date":"2024-06-17","arxiv_id":"2406.12030","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/spa-vl-a-comprehensive-safety-preference#ran","syntology_url":"https://syntology.ai/paper/2406.12030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12030"}},"official":{"repos":["echosechen/spa-vl-rlhf"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sugarcrepe-dataset-vision-language-model","slug":"sugarcrepe-dataset-vision-language-model","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","date":"2024-06-17","arxiv_id":"2406.11171","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":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) · 1 unverified","sample_list":"/paper/sugarcrepe-dataset-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2406.11171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11171"}},"official":{"repos":["Sri-Harsha/scpp"],"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/uniglm-training-one-unified-language-model","slug":"uniglm-training-one-unified-language-model","title":"UniGLM: Training One Unified Language Model for Text-Attributed Graph Embedding","date":"2024-06-17","arxiv_id":"2406.12052","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/uniglm-training-one-unified-language-model#ran","syntology_url":"https://syntology.ai/paper/2406.12052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12052"}},"official":{"repos":["nyushcs/uniglm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unveiling-encoder-free-vision-language-models","slug":"unveiling-encoder-free-vision-language-models","title":"Unveiling Encoder-Free Vision-Language Models","date":"2024-06-17","arxiv_id":"2406.11832","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/unveiling-encoder-free-vision-language-models#ran","syntology_url":"https://syntology.ai/paper/2406.11832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11832"}},"official":{"repos":["baaivision/eve"],"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":["unlocated"]}}},{"url":"/paper/watch-every-step-llm-agent-learning-via","slug":"watch-every-step-llm-agent-learning-via","title":"Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement","date":"2024-06-17","arxiv_id":"2406.11176","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/watch-every-step-llm-agent-learning-via#ran","syntology_url":"https://syntology.ai/paper/2406.11176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11176"}},"official":{"repos":["weiminxiong/ipr"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/avoiding-copyright-infringement-via-machine","slug":"avoiding-copyright-infringement-via-machine","title":"Avoiding Copyright Infringement via Large Language Model Unlearning","date":"2024-06-16","arxiv_id":"2406.10952","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":4,"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/avoiding-copyright-infringement-via-machine#ran","syntology_url":"https://syntology.ai/paper/2406.10952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10952"}},"official":{"repos":["guangyaodou/SSU_Unlearn"],"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/crisissense-llm-instruction-fine-tuned-large","slug":"crisissense-llm-instruction-fine-tuned-large","title":"CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics","date":"2024-06-16","arxiv_id":"2406.15477","repositories_listed":1,"syntology":null},{"url":"/paper/micl-improving-in-context-learning-through","slug":"micl-improving-in-context-learning-through","title":"Logit Separability-Driven Samples and Multiple Class-Related Words Selection for Advancing In-Context Learning","date":"2024-06-16","arxiv_id":"2406.10908","repositories_listed":1,"syntology":null},{"url":"/paper/not-all-bias-is-bad-balancing-rational","slug":"not-all-bias-is-bad-balancing-rational","title":"Balancing Rigor and Utility: Mitigating Cognitive Biases in Large Language Models for Multiple-Choice Questions","date":"2024-06-16","arxiv_id":"2406.10999","repositories_listed":1,"syntology":null},{"url":"/paper/optimization-of-armv9-architecture-general","slug":"optimization-of-armv9-architecture-general","title":"Optimization of Armv9 architecture general large language model inference performance based on Llama.cpp","date":"2024-06-16","arxiv_id":"2406.10816","repositories_listed":1,"syntology":null},{"url":"/paper/roselora-row-and-column-wise-sparse-low-rank","slug":"roselora-row-and-column-wise-sparse-low-rank","title":"RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning","date":"2024-06-16","arxiv_id":"2406.10777","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/roselora-row-and-column-wise-sparse-low-rank#ran","syntology_url":"https://syntology.ai/paper/2406.10777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10777"}},"official":{"repos":["lliutianc/roselora"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sharelora-parameter-efficient-and-robust","slug":"sharelora-parameter-efficient-and-robust","title":"ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.10785","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/sharelora-parameter-efficient-and-robust#ran","syntology_url":"https://syntology.ai/paper/2406.10785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10785"}},"official":{"repos":["Rain9876/ShareLoRA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/augmenting-biomedical-named-entity","slug":"augmenting-biomedical-named-entity","title":"Augmenting Biomedical Named Entity Recognition with General-domain Resources","date":"2024-06-15","arxiv_id":"2406.10671","repositories_listed":1,"syntology":null},{"url":"/paper/color-filter-conditional-loss-reduction","slug":"color-filter-conditional-loss-reduction","title":"CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training","date":"2024-06-15","arxiv_id":"2406.10670","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":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) · 1 unverified","sample_list":"/paper/color-filter-conditional-loss-reduction#ran","syntology_url":"https://syntology.ai/paper/2406.10670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10670"}},"official":{"repos":["davidbrandfonbrener/color-filter-olmo"],"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/self-supervised-representation-learning-with-5","slug":"self-supervised-representation-learning-with-5","title":"Self-Supervised Representation Learning with Spatial-Temporal Consistency for Sign Language Recognition","date":"2024-06-15","arxiv_id":"2406.10501","repositories_listed":1,"syntology":null},{"url":"/paper/spuriousness-aware-meta-learning-for-learning","slug":"spuriousness-aware-meta-learning-for-learning","title":"Spuriousness-Aware Meta-Learning for Learning Robust Classifiers","date":"2024-06-15","arxiv_id":"2406.10742","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/spuriousness-aware-meta-learning-for-learning#ran","syntology_url":"https://syntology.ai/paper/2406.10742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10742"}},"official":{"repos":["gtzheng/SPUME"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/beacon-benchmark-for-comprehensive-rna-tasks","slug":"beacon-benchmark-for-comprehensive-rna-tasks","title":"BEACON: Benchmark for Comprehensive RNA Tasks and Language Models","date":"2024-06-14","arxiv_id":"2406.10391","repositories_listed":1,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/beacon-benchmark-for-comprehensive-rna-tasks#ran","syntology_url":"https://syntology.ai/paper/2406.10391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10391"}},"official":{"repos":["terry-r123/RNABenchmark"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/carllava-vision-language-models-for-camera","slug":"carllava-vision-language-models-for-camera","title":"CarLLaVA: Vision language models for camera-only closed-loop driving","date":"2024-06-14","arxiv_id":"2406.10165","repositories_listed":1,"syntology":null},{"url":"/paper/group-and-shuffle-efficient-structured","slug":"group-and-shuffle-efficient-structured","title":"Group and Shuffle: Efficient Structured Orthogonal Parametrization","date":"2024-06-14","arxiv_id":"2406.10019","repositories_listed":1,"syntology":null},{"url":"/paper/let-the-poem-hit-the-rhythm-using-a-byte","slug":"let-the-poem-hit-the-rhythm-using-a-byte","title":"Let the Poem Hit the Rhythm: Using a Byte-Based Transformer for Beat-Aligned Poetry Generation","date":"2024-06-14","arxiv_id":"2406.10174","repositories_listed":1,"syntology":null},{"url":"/paper/luma-a-benchmark-dataset-for-learning-from","slug":"luma-a-benchmark-dataset-for-learning-from","title":"LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data","date":"2024-06-14","arxiv_id":"2406.09864","repositories_listed":1,"syntology":null},{"url":"/paper/rapport-driven-virtual-agent-rapport-building","slug":"rapport-driven-virtual-agent-rapport-building","title":"Rapport-Driven Virtual Agent: Rapport Building Dialogue Strategy for Improving User Experience at First Meeting","date":"2024-06-14","arxiv_id":"2406.09839","repositories_listed":1,"syntology":null},{"url":"/paper/sycophancy-to-subterfuge-investigating-reward","slug":"sycophancy-to-subterfuge-investigating-reward","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","date":"2024-06-14","arxiv_id":"2406.10162","repositories_listed":1,"syntology":null},{"url":"/paper/the-devil-is-in-the-neurons-interpreting-and","slug":"the-devil-is-in-the-neurons-interpreting-and","title":"The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models","date":"2024-06-14","arxiv_id":"2406.10130","repositories_listed":1,"syntology":null},{"url":"/paper/common-and-rare-fundus-diseases","slug":"common-and-rare-fundus-diseases","title":"Enhancing Diagnostic Accuracy in Rare and Common Fundus Diseases with a Knowledge-Rich Vision-Language Model","date":"2024-06-13","arxiv_id":"2406.09317","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":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/common-and-rare-fundus-diseases#ran","syntology_url":"https://syntology.ai/paper/2406.09317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09317"}},"official":{"repos":["LooKing9218/RetiZero"],"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/conceptual-learning-via-embedding","slug":"conceptual-learning-via-embedding","title":"Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency","date":"2024-06-13","arxiv_id":"2406.08840","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-domain-adaptation-through-prompt","slug":"enhancing-domain-adaptation-through-prompt","title":"Enhancing Domain Adaptation through Prompt Gradient Alignment","date":"2024-06-13","arxiv_id":"2406.09353","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"7 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/enhancing-domain-adaptation-through-prompt#ran","syntology_url":"https://syntology.ai/paper/2406.09353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09353"}},"official":{"repos":["viethoang1512/pga"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/explore-the-limits-of-omni-modal-pretraining","slug":"explore-the-limits-of-omni-modal-pretraining","title":"Explore the Limits of Omni-modal Pretraining at Scale","date":"2024-06-13","arxiv_id":"2406.09412","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-translation-capabilities-of","slug":"investigating-the-translation-capabilities-of","title":"Investigating the translation capabilities of Large Language Models trained on parallel data only","date":"2024-06-13","arxiv_id":"2406.09140","repositories_listed":1,"syntology":null},{"url":"/paper/newswire-a-large-scale-structured-database-of","slug":"newswire-a-large-scale-structured-database-of","title":"Newswire: A Large-Scale Structured Database of a Century of Historical News","date":"2024-06-13","arxiv_id":"2406.09490","repositories_listed":1,"syntology":null},{"url":"/paper/on-softmax-direct-preference-optimization-for","slug":"on-softmax-direct-preference-optimization-for","title":"On Softmax Direct Preference Optimization for Recommendation","date":"2024-06-13","arxiv_id":"2406.09215","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/on-softmax-direct-preference-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2406.09215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09215"}},"official":{"repos":["chenyuxin1999/s-dpo"],"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/proxylm-predicting-language-model-performance","slug":"proxylm-predicting-language-model-performance","title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models","date":"2024-06-13","arxiv_id":"2406.09334","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/proxylm-predicting-language-model-performance#ran","syntology_url":"https://syntology.ai/paper/2406.09334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09334"}},"official":{"repos":["davidanugraha/proxylm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/streambench-towards-benchmarking-continuous","slug":"streambench-towards-benchmarking-continuous","title":"StreamBench: Towards Benchmarking Continuous Improvement of Language Agents","date":"2024-06-13","arxiv_id":"2406.08747","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":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/streambench-towards-benchmarking-continuous#ran","syntology_url":"https://syntology.ai/paper/2406.08747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08747"}},"official":{"repos":["stream-bench/stream-bench"],"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/advancing-high-resolution-vision-language","slug":"advancing-high-resolution-vision-language","title":"Advancing High Resolution Vision-Language Models in Biomedicine","date":"2024-06-12","arxiv_id":"2406.09454","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-mamba-based-language","slug":"an-empirical-study-of-mamba-based-language","title":"An Empirical Study of Mamba-based Language Models","date":"2024-06-12","arxiv_id":"2406.07887","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-constrained-llm-through-pdfa","slug":"analyzing-constrained-llm-through-pdfa","title":"Analyzing constrained LLM through PDFA-learning","date":"2024-06-12","arxiv_id":"2406.08269","repositories_listed":1,"syntology":null},{"url":"/paper/collective-constitutional-ai-aligning-a","slug":"collective-constitutional-ai-aligning-a","title":"Collective Constitutional AI: Aligning a Language Model with Public Input","date":"2024-06-12","arxiv_id":"2406.07814","repositories_listed":1,"syntology":null},{"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/dataset-and-lessons-learned-from-the-2024","slug":"dataset-and-lessons-learned-from-the-2024","title":"Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition","date":"2024-06-12","arxiv_id":"2406.07954","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/dataset-and-lessons-learned-from-the-2024#ran","syntology_url":"https://syntology.ai/paper/2406.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07954"}},"official":{"repos":["ethz-spylab/ctf-satml24-data-analysis"],"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/figuratively-speaking-authorship-attribution","slug":"figuratively-speaking-authorship-attribution","title":"Figuratively Speaking: Authorship Attribution via Multi-Task Figurative Language Modeling","date":"2024-06-12","arxiv_id":"2406.08218","repositories_listed":1,"syntology":null},{"url":"/paper/flash-vstream-memory-based-real-time","slug":"flash-vstream-memory-based-real-time","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","date":"2024-06-12","arxiv_id":"2406.08085","repositories_listed":1,"syntology":null},{"url":"/paper/guiding-in-context-learning-of-llms-through","slug":"guiding-in-context-learning-of-llms-through","title":"Guiding In-Context Learning of LLMs through Quality Estimation for Machine Translation","date":"2024-06-12","arxiv_id":"2406.07970","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-council-benchmarking","slug":"language-model-council-benchmarking","title":"Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks","date":"2024-06-12","arxiv_id":"2406.08598","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-unlearning-via-embedding","slug":"large-language-model-unlearning-via-embedding","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","date":"2024-06-12","arxiv_id":"2406.07933","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/large-language-model-unlearning-via-embedding#ran","syntology_url":"https://syntology.ai/paper/2406.07933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07933"}},"official":{"repos":["chrisliu298/llm-unlearn-eco"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/multimodal-table-understanding","slug":"multimodal-table-understanding","title":"Multimodal Table Understanding","date":"2024-06-12","arxiv_id":"2406.08100","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multimodal-table-understanding#ran","syntology_url":"https://syntology.ai/paper/2406.08100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08100"}},"official":{"repos":["spursgozmy/table-llava"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/visionllm-v2-an-end-to-end-generalist","slug":"visionllm-v2-an-end-to-end-generalist","title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","date":"2024-06-12","arxiv_id":"2406.08394","repositories_listed":1,"syntology":null},{"url":"/paper/bvsp-broad-view-soft-prompting-for-few-shot","slug":"bvsp-broad-view-soft-prompting-for-few-shot","title":"BvSP: Broad-view Soft Prompting for Few-Shot Aspect Sentiment Quad Prediction","date":"2024-06-11","arxiv_id":"2406.07365","repositories_listed":1,"syntology":null},{"url":"/paper/mambalrp-explaining-selective-state-space","slug":"mambalrp-explaining-selective-state-space","title":"MambaLRP: Explaining Selective State Space Sequence Models","date":"2024-06-11","arxiv_id":"2406.07592","repositories_listed":1,"syntology":null},{"url":"/paper/multi-objective-reinforcement-learning-from","slug":"multi-objective-reinforcement-learning-from","title":"Multi-objective Reinforcement learning from AI Feedback","date":"2024-06-11","arxiv_id":"2406.07295","repositories_listed":1,"syntology":null},{"url":"/paper/paying-more-attention-to-source-context","slug":"paying-more-attention-to-source-context","title":"Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model","date":"2024-06-11","arxiv_id":"2406.07036","repositories_listed":1,"syntology":null},{"url":"/paper/rs-agent-automating-remote-sensing-tasks","slug":"rs-agent-automating-remote-sensing-tasks","title":"RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent","date":"2024-06-11","arxiv_id":"2406.07089","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/rs-agent-automating-remote-sensing-tasks#ran","syntology_url":"https://syntology.ai/paper/2406.07089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07089"}},"official":{"repos":["intellisensing/rs-agent"],"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/scaling-large-language-model-based-multi","slug":"scaling-large-language-model-based-multi","title":"Scaling Large Language Model-based Multi-Agent Collaboration","date":"2024-06-11","arxiv_id":"2406.07155","repositories_listed":1,"syntology":null},{"url":"/paper/scholarly-question-answering-using-large","slug":"scholarly-question-answering-using-large","title":"Scholarly Question Answering using Large Language Models in the NFDI4DataScience Gateway","date":"2024-06-11","arxiv_id":"2406.07257","repositories_listed":1,"syntology":null},{"url":"/paper/versicode-towards-version-controllable-code","slug":"versicode-towards-version-controllable-code","title":"VersiCode: Towards Version-controllable Code Generation","date":"2024-06-11","arxiv_id":"2406.07411","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-of-t-cell-receptor","slug":"contrastive-learning-of-t-cell-receptor","title":"Contrastive learning of T cell receptor representations","date":"2024-06-10","arxiv_id":"2406.06397","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-rpo-aligning-diffusion-models","slug":"diffusion-rpo-aligning-diffusion-models","title":"Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization","date":"2024-06-10","arxiv_id":"2406.06382","repositories_listed":1,"syntology":null},{"url":"/paper/mates-model-aware-data-selection-for","slug":"mates-model-aware-data-selection-for","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","date":"2024-06-10","arxiv_id":"2406.06046","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":8,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mates-model-aware-data-selection-for#ran","syntology_url":"https://syntology.ai/paper/2406.06046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06046"}},"official":{"repos":["cxcscmu/mates"],"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/powerinfer-2-fast-large-language-model","slug":"powerinfer-2-fast-large-language-model","title":"PowerInfer-2: Fast Large Language Model Inference on a Smartphone","date":"2024-06-10","arxiv_id":"2406.06282","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"6 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/powerinfer-2-fast-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2406.06282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06282"}},"official":null}},{"url":"/paper/sciriff-a-resource-to-enhance-language-model","slug":"sciriff-a-resource-to-enhance-language-model","title":"SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature","date":"2024-06-10","arxiv_id":"2406.07835","repositories_listed":1,"syntology":null},{"url":"/paper/trins-towards-multimodal-language-models-that","slug":"trins-towards-multimodal-language-models-that","title":"TRINS: Towards Multimodal Language Models that Can Read","date":"2024-06-10","arxiv_id":"2406.06730","repositories_listed":1,"syntology":null},{"url":"/paper/vcr-visual-caption-restoration","slug":"vcr-visual-caption-restoration","title":"VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text","date":"2024-06-10","arxiv_id":"2406.06462","repositories_listed":1,"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":10,"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/vcr-visual-caption-restoration#ran","syntology_url":"https://syntology.ai/paper/2406.06462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06462"}},"official":{"repos":["tianyu-z/vcr"],"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/a-survey-on-llm-based-agentic-workflows-and","slug":"a-survey-on-llm-based-agentic-workflows-and","title":"A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning","date":"2024-06-09","arxiv_id":"2406.05804","repositories_listed":1,"syntology":null},{"url":"/paper/growover-how-can-llms-adapt-to-growing-real","slug":"growover-how-can-llms-adapt-to-growing-real","title":"GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge?","date":"2024-06-09","arxiv_id":"2406.05606","repositories_listed":1,"syntology":null},{"url":"/paper/seventeenth-century-spanish-american-notary","slug":"seventeenth-century-spanish-american-notary","title":"Seventeenth-Century Spanish American Notary Records for Fine-Tuning Spanish Large Language Models","date":"2024-06-09","arxiv_id":"2406.05812","repositories_listed":1,"syntology":null},{"url":"/paper/soundscape-captioning-using-sound-affective","slug":"soundscape-captioning-using-sound-affective","title":"Soundscape Captioning using Sound Affective Quality Network and Large Language Model","date":"2024-06-09","arxiv_id":"2406.05914","repositories_listed":1,"syntology":null},{"url":"/paper/a-fine-tuning-dataset-and-benchmark-for-large","slug":"a-fine-tuning-dataset-and-benchmark-for-large","title":"A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding","date":"2024-06-08","arxiv_id":"2406.05540","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-fine-tuning-dataset-and-benchmark-for-large#ran","syntology_url":"https://syntology.ai/paper/2406.05540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05540"}},"official":{"repos":["tsynbio/proteinlmdataset"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-assisted-adversarial","slug":"large-language-model-assisted-adversarial","title":"Large Language Model Assisted Adversarial Robustness Neural Architecture Search","date":"2024-06-08","arxiv_id":"2406.05433","repositories_listed":1,"syntology":null},{"url":"/paper/ptf-fsr-a-parameter-transmission-free","slug":"ptf-fsr-a-parameter-transmission-free","title":"PTF-FSR: A Parameter Transmission-Free Federated Sequential Recommender System","date":"2024-06-08","arxiv_id":"2406.05387","repositories_listed":1,"syntology":null},{"url":"/paper/regularized-training-with-generated-datasets","slug":"regularized-training-with-generated-datasets","title":"Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models","date":"2024-06-08","arxiv_id":"2406.05432","repositories_listed":1,"syntology":null},{"url":"/paper/do-language-models-exhibit-human-like","slug":"do-language-models-exhibit-human-like","title":"Do Language Models Exhibit Human-like Structural Priming Effects?","date":"2024-06-07","arxiv_id":"2406.04847","repositories_listed":1,"syntology":null},{"url":"/paper/dualtime-a-dual-adapter-multimodal-language","slug":"dualtime-a-dual-adapter-multimodal-language","title":"MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning","date":"2024-06-07","arxiv_id":"2406.06620","repositories_listed":1,"syntology":null},{"url":"/paper/helpful-or-harmful-data-fine-tuning-free","slug":"helpful-or-harmful-data-fine-tuning-free","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","date":"2024-06-07","arxiv_id":"2406.04606","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"6 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/helpful-or-harmful-data-fine-tuning-free#ran","syntology_url":"https://syntology.ai/paper/2406.04606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04606"}},"official":{"repos":["jtwang2000/freeshap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"c9a9c192f7ae32cf52921b20a7d3e310d3b13ffae0b0445c9d6a2425f2592706","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}