{"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":"/method/gpt-3/papers/ran/1","list_of":"/method/gpt-3","method":"GPT-3","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":4,"rows_per_page":100,"rows":[1,100],"of":319,"counts":{"archive_papers_tagged":1906,"with_a_code_link":866,"where_syntology_ran_a_sample":319,"not_listed_spam_title":0,"listed":1906,"listed_where_code_ran":319,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":259,"every_run_a_failure_of_syntologys_instrument":60,"listed_with_a_run_with_no_instrument_failure":259,"listed_every_run_a_failure_of_syntologys_instrument":60,"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":"/method/gpt-3/papers/ran/1","prev":null,"next":"/method/gpt-3/papers/ran/2","papers":[{"paper":"/paper/healthbench-evaluating-large-language-models","slug":"healthbench-evaluating-large-language-models","title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","date":"2025-05-13","arxiv_id":"2505.08775","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["openai/simple-evals"],"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"]}}},{"paper":"/paper/context-aware-biases-for-length-extrapolation","slug":"context-aware-biases-for-length-extrapolation","title":"Context-aware Biases for Length Extrapolation","date":"2025-03-11","arxiv_id":"2503.08067","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["axiomlab/Cable"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/kbqa-o1-agentic-knowledge-base-question","slug":"kbqa-o1-agentic-knowledge-base-question","title":"KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search","date":"2025-01-31","arxiv_id":"2501.18922","n_code_links":1,"syntology":{"ran":2,"of":8,"n_ran_checked":2,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["lhrlab/kbqa-o1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/predicting-the-performance-of-black-box-llms","slug":"predicting-the-performance-of-black-box-llms","title":"Predicting the Performance of Black-box LLMs through Self-Queries","date":"2025-01-02","arxiv_id":"2501.01558","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dsam99/quere"],"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"]}}},{"paper":"/paper/training-and-evaluating-language-models-with","slug":"training-and-evaluating-language-models-with","title":"Training and Evaluating Language Models with Template-based Data Generation","date":"2024-11-27","arxiv_id":"2411.18104","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["iiis-ai/templatemath"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/perfcodegen-improving-performance-of-llm","slug":"perfcodegen-improving-performance-of-llm","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","date":"2024-11-18","arxiv_id":"2412.03578","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["SalesforceAIResearch/perfcodegen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/fair-summarization-bridging-quality-and","slug":"fair-summarization-bridging-quality-and","title":"Fair Summarization: Bridging Quality and Diversity in Extractive Summaries","date":"2024-11-12","arxiv_id":"2411.07521","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["PortNLP/FairEXTSummarizer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/selfcodealign-self-alignment-for-code","slug":"selfcodealign-self-alignment-for-code","title":"SelfCodeAlign: Self-Alignment for Code Generation","date":"2024-10-31","arxiv_id":"2410.24198","n_code_links":2,"syntology":{"ran":30,"of":37,"n_ran_checked":22,"n_instrument":8,"unverified":7,"pointer_only":0,"phrase":"30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified","official":{"repos":["bigcode-project/selfcodealign"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["community","listed","official"]}}},{"paper":"/paper/scaling-up-masked-diffusion-models-on-text","slug":"scaling-up-masked-diffusion-models-on-text","title":"Scaling up Masked Diffusion Models on Text","date":"2024-10-24","arxiv_id":"2410.18514","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ml-gsai/smdm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"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","official":null}},{"paper":"/paper/the-rise-of-ai-generated-content-in-wikipedia","slug":"the-rise-of-ai-generated-content-in-wikipedia","title":"The Rise of AI-Generated Content in Wikipedia","date":"2024-10-10","arxiv_id":"2410.08044","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":8,"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","official":{"repos":["brooksca3/wiki_collection"],"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"]}}},{"paper":"/paper/take-it-easy-label-adaptive-self","slug":"take-it-easy-label-adaptive-self","title":"Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation","date":"2024-10-05","arxiv_id":"2410.04002","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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","official":{"repos":["jingyng/label-adaptive-self-rationalization"],"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"]}}},{"paper":"/paper/codejudge-evaluating-code-generation-with","slug":"codejudge-evaluating-code-generation-with","title":"CodeJudge: Evaluating Code Generation with Large Language Models","date":"2024-10-03","arxiv_id":"2410.02184","n_code_links":1,"syntology":{"ran":15,"of":23,"n_ran_checked":14,"n_instrument":1,"unverified":8,"pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["VichyTong/CodeJudge"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":7,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/alignsum-data-pyramid-hierarchical-fine","slug":"alignsum-data-pyramid-hierarchical-fine","title":"AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference","date":"2024-10-01","arxiv_id":"2410.00409","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["csyanghan/alignsum"],"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"]}}},{"paper":"/paper/maskllm-learnable-semi-structured-sparsity","slug":"maskllm-learnable-semi-structured-sparsity","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","date":"2024-09-26","arxiv_id":"2409.17481","n_code_links":1,"syntology":{"ran":5,"of":16,"n_ran_checked":5,"n_instrument":0,"unverified":11,"pointer_only":16,"phrase":"5 ran (of which 1 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) · 11 unverified","official":{"repos":["nvlabs/maskllm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":"/paper/effective-and-evasive-fuzz-testing-driven","slug":"effective-and-evasive-fuzz-testing-driven","title":"PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs","date":"2024-09-23","arxiv_id":"2409.14866","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["aaFrostnova/Papillon"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/neural-symbolic-collaborative-distillation","slug":"neural-symbolic-collaborative-distillation","title":"Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks","date":"2024-09-20","arxiv_id":"2409.13203","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":7,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xnhyacinth/nesycd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/magicore-multi-agent-iterative-coarse-to-fine","slug":"magicore-multi-agent-iterative-coarse-to-fine","title":"MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning","date":"2024-09-18","arxiv_id":"2409.12147","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dinobby/magicore"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-large-language-models-unlock-novel","slug":"can-large-language-models-unlock-novel","title":"Can Large Language Models Unlock Novel Scientific Research Ideas?","date":"2024-09-10","arxiv_id":"2409.06185","n_code_links":1,"syntology":{"ran":2,"of":11,"n_ran_checked":2,"n_instrument":0,"unverified":9,"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) · 9 unverified","official":{"repos":["sandeep82945/future-idea-generation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-judge-selective-instruction-following","slug":"self-judge-selective-instruction-following","title":"Self-Judge: Selective Instruction Following with Alignment Self-Evaluation","date":"2024-09-02","arxiv_id":"2409.00935","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["nusnlp/Self-J"],"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"]}}},{"paper":"/paper/unlocking-adversarial-suffix-optimization","slug":"unlocking-adversarial-suffix-optimization","title":"Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer","date":"2024-08-21","arxiv_id":"2408.11313","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"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","official":{"repos":["lenijwp/eclipse"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/2408-00764","slug":"2408-00764","title":"AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation","date":"2024-08-01","arxiv_id":"2408.00764","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["lazychih114/AgentGen-Reproduction"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/peft-u-parameter-efficient-fine-tuning-for","slug":"peft-u-parameter-efficient-fine-tuning-for","title":"PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization","date":"2024-07-25","arxiv_id":"2407.18078","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"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","official":{"repos":["ChrisIsKing/Parameter-Efficient-Personalization"],"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"]}}},{"paper":"/paper/enhancing-llm-s-cognition-via-structurization","slug":"enhancing-llm-s-cognition-via-structurization","title":"Enhancing LLM's Cognition via Structurization","date":"2024-07-23","arxiv_id":"2407.16434","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"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","official":{"repos":["alibaba/struxgpt"],"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"]}}},{"paper":"/paper/data-mixture-inference-what-do-bpe-tokenizers","slug":"data-mixture-inference-what-do-bpe-tokenizers","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","date":"2024-07-23","arxiv_id":"2407.16607","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["alisawuffles/tokenizer-attack"],"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"]}}},{"paper":"/paper/mminstruct-a-high-quality-multi-modal","slug":"mminstruct-a-high-quality-multi-modal","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","date":"2024-07-22","arxiv_id":"2407.15838","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yuecao0119/mminstruct"],"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"]}}},{"paper":"/paper/does-refusal-training-in-llms-generalize-to","slug":"does-refusal-training-in-llms-generalize-to","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","date":"2024-07-16","arxiv_id":"2407.11969","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["tml-epfl/llm-past-tense"],"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"]}}},{"paper":"/paper/think-on-graph-2-0-deep-and-interpretable","slug":"think-on-graph-2-0-deep-and-interpretable","title":"Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation","date":"2024-07-15","arxiv_id":"2407.10805","n_code_links":1,"syntology":{"ran":13,"of":16,"n_ran_checked":13,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["idea-finai/tog-2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/inversecoder-unleashing-the-power-of","slug":"inversecoder-unleashing-the-power-of","title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct","date":"2024-07-08","arxiv_id":"2407.05700","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":11,"n_instrument":0,"unverified":0,"pointer_only":11,"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) · 0 unverified","official":{"repos":["wyt2000/InverseCoder"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/shine-saliency-aware-hierarchical-negative","slug":"shine-saliency-aware-hierarchical-negative","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","date":"2024-07-06","arxiv_id":"2407.05118","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zxccade/shine"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/sop-unlock-the-power-of-social-facilitation","slug":"sop-unlock-the-power-of-social-facilitation","title":"SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters","date":"2024-07-02","arxiv_id":"2407.01902","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["yang-yan-yang-yan/sop"],"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"]}}},{"paper":"/paper/multilingual-trolley-problems-for-language","slug":"multilingual-trolley-problems-for-language","title":"Language Model Alignment in Multilingual Trolley Problems","date":"2024-07-02","arxiv_id":"2407.02273","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["causalNLP/moralmachine","causalnlp/multitp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/increasing-model-capacity-for-free-a-simple","slug":"increasing-model-capacity-for-free-a-simple","title":"Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning","date":"2024-07-01","arxiv_id":"2407.01320","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":6,"n_instrument":1,"unverified":3,"pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["lins-lab/capaboost"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/shortcutsbench-a-large-scale-real-world","slug":"shortcutsbench-a-large-scale-real-world","title":"ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents","date":"2024-06-28","arxiv_id":"2407.00132","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eachsheep/shortcutsbench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-to-plan-for-retrieval-augmented","slug":"learning-to-plan-for-retrieval-augmented","title":"Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs","date":"2024-06-20","arxiv_id":"2406.14282","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zjukg/lpkg"],"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"]}}},{"paper":"/paper/llasa-large-multimodal-agent-for-human","slug":"llasa-large-multimodal-agent-for-human","title":"LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors","date":"2024-06-20","arxiv_id":"2406.14498","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":3,"n_instrument":3,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bashlab/llasa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/prism-a-framework-for-decoupling-and","slug":"prism-a-framework-for-decoupling-and","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","date":"2024-06-20","arxiv_id":"2406.14544","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["sparksjoe/prism"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/part-aware-unified-representation-of-language-1","slug":"part-aware-unified-representation-of-language-1","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","date":"2024-06-19","arxiv_id":"2406.13327","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["azzh1/purls"],"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"]}}},{"paper":"/paper/towards-a-client-centered-assessment-of-llm","slug":"towards-a-client-centered-assessment-of-llm","title":"Towards a Client-Centered Assessment of LLM Therapists by Client Simulation","date":"2024-06-18","arxiv_id":"2406.12266","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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","official":{"repos":["wangjs9/clientcast"],"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"]}}},{"paper":"/paper/welldunn-on-the-robustness-and-explainability","slug":"welldunn-on-the-robustness-and-explainability","title":"WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions","date":"2024-06-17","arxiv_id":"2406.12058","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vedantpalit/WellDunn"],"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"]}}},{"paper":"/paper/fine-tuned-small-llms-still-significantly","slug":"fine-tuned-small-llms-still-significantly","title":"Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification","date":"2024-06-12","arxiv_id":"2406.08660","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":9,"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) · 4 unverified","official":{"repos":["mnbucher/text-cls-llms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/berts-are-generative-in-context-learners","slug":"berts-are-generative-in-context-learners","title":"BERTs are Generative In-Context Learners","date":"2024-06-07","arxiv_id":"2406.04823","n_code_links":1,"syntology":{"ran":13,"of":26,"n_ran_checked":12,"n_instrument":1,"unverified":13,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified","official":{"repos":["ltgoslo/bert-in-context"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":13,"ran_from_kinds":["official"]}}},{"paper":"/paper/gamebench-evaluating-strategic-reasoning","slug":"gamebench-evaluating-strategic-reasoning","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","date":"2024-06-07","arxiv_id":"2406.06613","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["Joshuaclymer/GameBench"],"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"]}}},{"paper":"/paper/semcoder-training-code-language-models-with","slug":"semcoder-training-code-language-models-with","title":"SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning","date":"2024-06-03","arxiv_id":"2406.01006","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":10,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["arise-lab/semcoder"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/evaluating-mathematical-reasoning-of-large","slug":"evaluating-mathematical-reasoning-of-large","title":"Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction","date":"2024-06-02","arxiv_id":"2406.00755","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["littlecirc1e/eic"],"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"]}}},{"paper":"/paper/large-language-models-are-zero-shot-next","slug":"large-language-models-are-zero-shot-next","title":"Large Language Models are Zero-Shot Next Location Predictors","date":"2024-05-31","arxiv_id":"2405.20962","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["ssai-trento/llm-zero-shot-nl"],"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"]}}},{"paper":"/paper/anah-analytical-annotation-of-hallucinations","slug":"anah-analytical-annotation-of-hallucinations","title":"ANAH: Analytical Annotation of Hallucinations in Large Language Models","date":"2024-05-30","arxiv_id":"2405.20315","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["open-compass/anah"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/aligning-to-thousands-of-preferences-via","slug":"aligning-to-thousands-of-preferences-via","title":"Aligning to Thousands of Preferences via System Message Generalization","date":"2024-05-28","arxiv_id":"2405.17977","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kaistAI/Janus"],"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":["community","official"]}}},{"paper":"/paper/an-empirical-analysis-on-large-language","slug":"an-empirical-analysis-on-large-language","title":"An Empirical Analysis on Large Language Models in Debate Evaluation","date":"2024-05-28","arxiv_id":"2406.00050","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["xinyiliu0227/llm_debate_bias"],"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"]}}},{"paper":"/paper/thread-thinking-deeper-with-recursive","slug":"thread-thinking-deeper-with-recursive","title":"THREAD: Thinking Deeper with Recursive Spawning","date":"2024-05-27","arxiv_id":"2405.17402","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["philipmit/thread"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/automanual-generating-instruction-manuals-by","slug":"automanual-generating-instruction-manuals-by","title":"AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning","date":"2024-05-25","arxiv_id":"2405.16247","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["minghchen/automanual"],"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"]}}},{"paper":"/paper/evaluating-the-adversarial-robustness-of-1","slug":"evaluating-the-adversarial-robustness-of-1","title":"Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning","date":"2024-05-24","arxiv_id":"2405.15984","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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","official":{"repos":["simonucl/adv-retreival-icl"],"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"]}}},{"paper":"/paper/editworld-simulating-world-dynamics-for","slug":"editworld-simulating-world-dynamics-for","title":"EditWorld: Simulating World Dynamics for Instruction-Following Image Editing","date":"2024-05-23","arxiv_id":"2405.14785","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yangling0818/editworld"],"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"]}}},{"paper":"/paper/eliciting-informative-text-evaluations-with","slug":"eliciting-informative-text-evaluations-with","title":"Eliciting Informative Text Evaluations with Large Language Models","date":"2024-05-23","arxiv_id":"2405.15077","n_code_links":1,"syntology":{"ran":10,"of":14,"n_ran_checked":8,"n_instrument":2,"unverified":4,"pointer_only":14,"phrase":"10 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yx-lu/eliciting-informative-text-evaluations-with-large-language-models"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/topa-extend-large-language-models-for-video","slug":"topa-extend-large-language-models-for-video","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","date":"2024-05-22","arxiv_id":"2405.13911","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":4,"n_instrument":2,"unverified":3,"pointer_only":3,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["dhg-wei/topa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/zero-shot-stance-detection-using-contextual","slug":"zero-shot-stance-detection-using-contextual","title":"Zero-Shot Stance Detection using Contextual Data Generation with LLMs","date":"2024-05-19","arxiv_id":"2405.11637","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["Babakbehkamkia/GPT-Stance-Detection"],"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"]}}},{"paper":"/paper/limited-ability-of-llms-to-simulate-human","slug":"limited-ability-of-llms-to-simulate-human","title":"Limited Ability of LLMs to Simulate Human Psychological Behaviours: a Psychometric Analysis","date":"2024-05-12","arxiv_id":"2405.07248","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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","official":{"repos":["nikbpetrov/llms-simulate-humans"],"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"]}}},{"paper":"/paper/hire-me-or-not-examining-language-model-s","slug":"hire-me-or-not-examining-language-model-s","title":"Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes","date":"2024-05-06","arxiv_id":"2405.06687","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["daminz97/multi-step_gsv"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/do-large-language-models-understand","slug":"do-large-language-models-understand","title":"Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcom","date":"2024-04-30","arxiv_id":"2404.19509","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":6,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["sjtu-compling/llm-pragmatics"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/worldvaluesbench-a-large-scale-benchmark","slug":"worldvaluesbench-a-large-scale-benchmark","title":"WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models","date":"2024-04-25","arxiv_id":"2404.16308","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"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","official":{"repos":["demon702/worldvaluesbench"],"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"]}}},{"paper":"/paper/how-well-can-llms-echo-us-evaluating-ai","slug":"how-well-can-llms-echo-us-evaluating-ai","title":"How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO","date":"2024-04-22","arxiv_id":"2404.13957","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":6,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cuhk-arise/echo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/svgeditbench-a-benchmark-dataset-for","slug":"svgeditbench-a-benchmark-dataset-for","title":"SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities","date":"2024-04-21","arxiv_id":"2404.13710","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["mti-lab/svgeditbench"],"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"]}}},{"paper":"/paper/from-form-s-to-meaning-probing-the-semantic","slug":"from-form-s-to-meaning-probing-the-semantic","title":"From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency","date":"2024-04-18","arxiv_id":"2404.12145","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["facebookresearch/multisense_consistency"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/utebc-nlp-at-semeval-2024-task-9-can-llms-be","slug":"utebc-nlp-at-semeval-2024-task-9-can-llms-be","title":"uTeBC-NLP at SemEval-2024 Task 9: Can LLMs be Lateral Thinkers?","date":"2024-04-03","arxiv_id":"2404.02474","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["ipouyall/can-llms-be-lateral-thinkers"],"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"]}}},{"paper":"/paper/advancing-llm-reasoning-generalists-with","slug":"advancing-llm-reasoning-generalists-with","title":"Advancing LLM Reasoning Generalists with Preference Trees","date":"2024-04-02","arxiv_id":"2404.02078","n_code_links":1,"syntology":{"ran":18,"of":20,"n_ran_checked":13,"n_instrument":5,"unverified":2,"pointer_only":2,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["openbmb/eurus"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/jailbreaking-leading-safety-aligned-llms-with","slug":"jailbreaking-leading-safety-aligned-llms-with","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","date":"2024-04-02","arxiv_id":"2404.02151","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tml-epfl/llm-adaptive-attacks"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/fables-evaluating-faithfulness-and-content","slug":"fables-evaluating-faithfulness-and-content","title":"FABLES: Evaluating faithfulness and content selection in book-length summarization","date":"2024-04-01","arxiv_id":"2404.01261","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["mungg/fables"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/vulnerability-detection-with-code-language","slug":"vulnerability-detection-with-code-language","title":"Vulnerability Detection with Code Language Models: How Far Are We?","date":"2024-03-27","arxiv_id":"2403.18624","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["dlvuldet/primevul"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/omnivid-a-generative-framework-for-universal","slug":"omnivid-a-generative-framework-for-universal","title":"OmniVid: A Generative Framework for Universal Video Understanding","date":"2024-03-26","arxiv_id":"2403.17935","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["wangjk666/omnivid"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/repairagent-an-autonomous-llm-based-agent-for","slug":"repairagent-an-autonomous-llm-based-agent-for","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","date":"2024-03-25","arxiv_id":"2403.17134","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sola-st/RepairAgent"],"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"]}}},{"paper":"/paper/how-far-are-we-on-the-decision-making-of-llms","slug":"how-far-are-we-on-the-decision-making-of-llms","title":"How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments","date":"2024-03-18","arxiv_id":"2403.11807","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cuhk-arise/gamabench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/easyjailbreak-a-unified-framework-for","slug":"easyjailbreak-a-unified-framework-for","title":"EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models","date":"2024-03-18","arxiv_id":"2403.12171","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["easyjailbreak/easyjailbreak"],"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"]}}},{"paper":"/paper/data-is-all-you-need-finetuning-llms-for-chip","slug":"data-is-all-you-need-finetuning-llms-for-chip","title":"Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework","date":"2024-03-17","arxiv_id":"2403.11202","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["aichipdesign/chipgptft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/codeultrafeedback-an-llm-as-a-judge-dataset","slug":"codeultrafeedback-an-llm-as-a-judge-dataset","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","date":"2024-03-14","arxiv_id":"2403.09032","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["martin-wey/codeultrafeedback"],"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"]}}},{"paper":"/paper/bias-augmented-consistency-training-reduces","slug":"bias-augmented-consistency-training-reduces","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","date":"2024-03-08","arxiv_id":"2403.05518","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":1,"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","official":{"repos":["raybears/cot-transparency"],"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"]}}},{"paper":"/paper/differentially-private-synthetic-data-via-1","slug":"differentially-private-synthetic-data-via-1","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","date":"2024-03-04","arxiv_id":"2403.01749","n_code_links":2,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["ai-secure/aug-pe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/sciassess-benchmarking-llm-proficiency-in","slug":"sciassess-benchmarking-llm-proficiency-in","title":"SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis","date":"2024-03-04","arxiv_id":"2403.01976","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["sci-assess/sciassess"],"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"]}}},{"paper":"/paper/serval-synergy-learning-between-vertical","slug":"serval-synergy-learning-between-vertical","title":"SERVAL: Synergy Learning between Vertical Models and LLMs towards Oracle-Level Zero-shot Medical Prediction","date":"2024-03-03","arxiv_id":"2403.01570","n_code_links":0,"syntology":{"ran":6,"of":8,"n_ran_checked":1,"n_instrument":5,"unverified":2,"pointer_only":0,"phrase":"6 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; 5 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/autodefense-multi-agent-llm-defense-against","slug":"autodefense-multi-agent-llm-defense-against","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","date":"2024-03-02","arxiv_id":"2403.04783","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xhmy/autodefense"],"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"]}}},{"paper":"/paper/keeping-llms-aligned-after-fine-tuning-the","slug":"keeping-llms-aligned-after-fine-tuning-the","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","date":"2024-02-28","arxiv_id":"2402.18540","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":5,"n_instrument":1,"unverified":4,"pointer_only":0,"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","official":{"repos":["vfleaking/ptst"],"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"]}}},{"paper":"/paper/measuring-vision-language-stem-skills-of","slug":"measuring-vision-language-stem-skills-of","title":"Measuring Vision-Language STEM Skills of Neural Models","date":"2024-02-27","arxiv_id":"2402.17205","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["stemdataset/STEM"],"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"]}}},{"paper":"/paper/chatmusician-understanding-and-generating","slug":"chatmusician-understanding-and-generating","title":"ChatMusician: Understanding and Generating Music Intrinsically with LLM","date":"2024-02-25","arxiv_id":"2402.16153","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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","official":{"repos":["hf-lin/ChatMusician"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/tokenization-counts-the-impact-of","slug":"tokenization-counts-the-impact-of","title":"Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs","date":"2024-02-22","arxiv_id":"2402.14903","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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","official":{"repos":["aadityasingh/tokenizationcounts"],"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"]}}},{"paper":"/paper/llm-jailbreak-attack-versus-defense","slug":"llm-jailbreak-attack-versus-defense","title":"A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models","date":"2024-02-21","arxiv_id":"2402.13457","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["ltroin/llm_attack_defense_arena"],"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"]}}},{"paper":"/paper/benchmarking-retrieval-augmented-generation","slug":"benchmarking-retrieval-augmented-generation","title":"Benchmarking Retrieval-Augmented Generation for Medicine","date":"2024-02-20","arxiv_id":"2402.13178","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["teddy-xionggz/medrag","teddy-xionggz/mirage"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-critical-evaluation-of-ai-feedback-for","slug":"a-critical-evaluation-of-ai-feedback-for","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","date":"2024-02-19","arxiv_id":"2402.12366","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":8,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["architsharma97/dpo-rlaif"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/perils-of-self-feedback-self-bias-amplifies","slug":"perils-of-self-feedback-self-bias-amplifies","title":"Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement","date":"2024-02-18","arxiv_id":"2402.11436","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xu1998hz/llm_self_bias"],"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"]}}},{"paper":"/paper/cold-attack-jailbreaking-llms-with","slug":"cold-attack-jailbreaking-llms-with","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","date":"2024-02-13","arxiv_id":"2402.08679","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":11,"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) · 4 unverified","official":{"repos":["yu-fangxu/cold-attack"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/prompt-optimization-in-multi-step-tasks","slug":"prompt-optimization-in-multi-step-tasks","title":"PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling","date":"2024-02-13","arxiv_id":"2402.08702","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"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","official":{"repos":["yongchao98/promst"],"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"]}}},{"paper":"/paper/measuring-and-controlling-instruction-in","slug":"measuring-and-controlling-instruction-in","title":"Measuring and Controlling Instruction (In)Stability in Language Model Dialogs","date":"2024-02-13","arxiv_id":"2402.10962","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":5,"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) · 3 unverified","official":{"repos":["likenneth/persona_drift"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/addressing-cognitive-bias-in-medical-language","slug":"addressing-cognitive-bias-in-medical-language","title":"Addressing cognitive bias in medical language models","date":"2024-02-12","arxiv_id":"2402.08113","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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","official":{"repos":["carlwharris/cog-bias-med-llms"],"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"]}}},{"paper":"/paper/culturellm-incorporating-cultural-differences","slug":"culturellm-incorporating-cultural-differences","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","date":"2024-02-09","arxiv_id":"2402.10946","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"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","official":{"repos":["scarelette/culturellm"],"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"]}}},{"paper":"/paper/comprehensive-assessment-of-jailbreak-attacks","slug":"comprehensive-assessment-of-jailbreak-attacks","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","date":"2024-02-08","arxiv_id":"2402.05668","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["TrustAIRLab/Comprehensive_Jailbreak_Assessment"],"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"]}}},{"paper":"/paper/grandmaster-level-chess-without-search","slug":"grandmaster-level-chess-without-search","title":"Amortized Planning with Large-Scale Transformers: A Case Study on Chess","date":"2024-02-07","arxiv_id":"2402.04494","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"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","official":{"repos":["google-deepmind/searchless_chess"],"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"]}}},{"paper":"/paper/long-is-more-for-alignment-a-simple-but-tough","slug":"long-is-more-for-alignment-a-simple-but-tough","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","date":"2024-02-07","arxiv_id":"2402.04833","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"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","official":{"repos":["tml-epfl/long-is-more-for-alignment"],"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","unlocated"]}}},{"paper":"/paper/training-language-models-to-generate-text","slug":"training-language-models-to-generate-text","title":"Training Language Models to Generate Text with Citations via Fine-grained Rewards","date":"2024-02-06","arxiv_id":"2402.04315","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":3,"n_instrument":4,"unverified":5,"pointer_only":1,"phrase":"7 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; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hcy123902/atg-w-fg-rw"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/gerea-question-aware-prompt-captions-for","slug":"gerea-question-aware-prompt-captions-for","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","date":"2024-02-04","arxiv_id":"2402.02503","n_code_links":1,"syntology":{"ran":13,"of":18,"n_ran_checked":13,"n_instrument":0,"unverified":5,"pointer_only":18,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["upper9527/gerea"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/effibench-benchmarking-the-efficiency-of","slug":"effibench-benchmarking-the-efficiency-of","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","date":"2024-02-03","arxiv_id":"2402.02037","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":5,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["huangd1999/EffiBench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mt-eval-a-multi-turn-capabilities-evaluation","slug":"mt-eval-a-multi-turn-capabilities-evaluation","title":"MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models","date":"2024-01-30","arxiv_id":"2401.16745","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["kwanwaichung/mt-eval"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/llamp-large-language-model-made-powerful-for","slug":"llamp-large-language-model-made-powerful-for","title":"LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation","date":"2024-01-30","arxiv_id":"2401.17244","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["chiang-yuan/llamp"],"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"]}}}],"record_sha256":"336e08aea74af6c1d76dba75c6002e264f139edcef0ccd837dbcfa01db93f27e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}