{"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/large-language-model/papers/2","list_of":"/task/large-language-model","task":"Large Language Model","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":2,"pages_in_order":61,"rows_per_page":100,"rows":[101,200],"of":6097,"counts":{"archive_papers_tagged":6097,"with_a_code_link":2250,"where_syntology_ran_a_sample":801,"not_listed_spam_title":0,"listed":6097,"listed_where_code_ran":801,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":683,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":683,"listed_every_run_a_failure_of_syntologys_instrument":118,"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/large-language-model","prev":"/task/large-language-model","next":"/task/large-language-model/papers/3","papers":[{"url":"/paper/llm-stability-a-detailed-analysis-with-some","slug":"llm-stability-a-detailed-analysis-with-some","title":"Non-Determinism of \"Deterministic\" LLM Settings","date":"2024-08-06","arxiv_id":"2408.04667","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 2 unverified","sample_list":"/paper/llm-stability-a-detailed-analysis-with-some#ran","syntology_url":"https://syntology.ai/paper/2408.04667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04667"}},"official":{"repos":["breckbaldwin/llm-stability","Comcast/llm-stability"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/illm-tsc-integration-reinforcement-learning","slug":"illm-tsc-integration-reinforcement-learning","title":"iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement","date":"2024-07-08","arxiv_id":"2407.06025","repositories_listed":2,"syntology":null},{"url":"/paper/minference-1-0-accelerating-pre-filling-for","slug":"minference-1-0-accelerating-pre-filling-for","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","date":"2024-07-02","arxiv_id":"2407.02490","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/minference-1-0-accelerating-pre-filling-for#ran","syntology_url":"https://syntology.ai/paper/2407.02490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02490"}},"official":{"repos":["microsoft/MInference"],"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":["listed","official"]}}},{"url":"/paper/mm-instruct-generated-visual-instructions-for","slug":"mm-instruct-generated-visual-instructions-for","title":"MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment","date":"2024-06-28","arxiv_id":"2406.19736","repositories_listed":2,"syntology":null},{"url":"/paper/omagent-a-multi-modal-agent-framework-for","slug":"omagent-a-multi-modal-agent-framework-for","title":"OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer","date":"2024-06-24","arxiv_id":"2406.16620","repositories_listed":2,"syntology":null},{"url":"/paper/a-llm-based-ranking-method-for-the-evaluation","slug":"a-llm-based-ranking-method-for-the-evaluation","title":"A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation","date":"2024-06-21","arxiv_id":"2406.15227","repositories_listed":2,"syntology":null},{"url":"/paper/autonomous-agents-for-collaborative-task","slug":"autonomous-agents-for-collaborative-task","title":"Autonomous Agents for Collaborative Task under Information Asymmetry","date":"2024-06-21","arxiv_id":"2406.14928","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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","sample_list":"/paper/autonomous-agents-for-collaborative-task#ran","syntology_url":"https://syntology.ai/paper/2406.14928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14928"}},"official":{"repos":["thinkwee/iAgents"],"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"]}}},{"url":"/paper/talk-with-human-like-agents-empathetic","slug":"talk-with-human-like-agents-empathetic","title":"Talk With Human-like Agents: Empathetic Dialogue Through Perceptible Acoustic Reception and Reaction","date":"2024-06-18","arxiv_id":"2406.12707","repositories_listed":2,"syntology":null},{"url":"/paper/fairer-preferences-elicit-improved-human","slug":"fairer-preferences-elicit-improved-human","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","date":"2024-06-17","arxiv_id":"2406.11370","repositories_listed":2,"syntology":{"n":29,"n_ran":20,"n_constructed":4,"n_ran_checked":10,"n_instrument":10,"n_unverified":9,"n_honours":3,"n_violates":2,"n_no_contract":5,"n_pointer_only":2,"phrase":"20 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 2 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/fairer-preferences-elicit-improved-human#ran","syntology_url":"https://syntology.ai/paper/2406.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11370"}},"official":{"repos":["cambridgeltl/zepo"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/large-scale-transfer-learning-for-tabular","slug":"large-scale-transfer-learning-for-tabular","title":"Large Scale Transfer Learning for Tabular Data via Language Modeling","date":"2024-06-17","arxiv_id":"2406.12031","repositories_listed":2,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/large-scale-transfer-learning-for-tabular#ran","syntology_url":"https://syntology.ai/paper/2406.12031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12031"}},"official":{"repos":["mlfoundations/rtfm","mlfoundations/tabliblib"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/crag-comprehensive-rag-benchmark","slug":"crag-comprehensive-rag-benchmark","title":"CRAG -- Comprehensive RAG Benchmark","date":"2024-06-07","arxiv_id":"2406.04744","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crag-comprehensive-rag-benchmark#ran","syntology_url":"https://syntology.ai/paper/2406.04744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04744"}},"official":{"repos":["facebookresearch/crag"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lawgpt-a-chinese-legal-knowledge-enhanced","slug":"lawgpt-a-chinese-legal-knowledge-enhanced","title":"LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model","date":"2024-06-07","arxiv_id":"2406.04614","repositories_listed":2,"syntology":null},{"url":"/paper/llm-based-rewriting-of-inappropriate","slug":"llm-based-rewriting-of-inappropriate","title":"LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback","date":"2024-06-05","arxiv_id":"2406.03363","repositories_listed":2,"syntology":null},{"url":"/paper/trutheval-a-dataset-to-evaluate-llm","slug":"trutheval-a-dataset-to-evaluate-llm","title":"TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability","date":"2024-06-04","arxiv_id":"2406.01855","repositories_listed":2,"syntology":null},{"url":"/paper/the-geometry-of-categorical-and-hierarchical","slug":"the-geometry-of-categorical-and-hierarchical","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","date":"2024-06-03","arxiv_id":"2406.01506","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/the-geometry-of-categorical-and-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2406.01506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01506"}},"official":{"repos":["kihopark/llm_categorical_hierarchical_representations"],"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"]}}},{"url":"/paper/llamea-a-large-language-model-evolutionary","slug":"llamea-a-large-language-model-evolutionary","title":"LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics","date":"2024-05-30","arxiv_id":"2405.20132","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/llamea-a-large-language-model-evolutionary#ran","syntology_url":"https://syntology.ai/paper/2405.20132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20132"}},"official":{"repos":["nikivanstein/LLaMEA"],"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":["listed","official"]}}},{"url":"/paper/llm-experiments-with-simulation-large","slug":"llm-experiments-with-simulation-large","title":"LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins","date":"2024-05-28","arxiv_id":"2405.18092","repositories_listed":2,"syntology":null},{"url":"/paper/chess-contextual-harnessing-for-efficient-sql","slug":"chess-contextual-harnessing-for-efficient-sql","title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","date":"2024-05-27","arxiv_id":"2405.16755","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/chess-contextual-harnessing-for-efficient-sql#ran","syntology_url":"https://syntology.ai/paper/2405.16755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16755"}},"official":{"repos":["shayantalaei/chess"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cacheblend-fast-large-language-model-serving","slug":"cacheblend-fast-large-language-model-serving","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","date":"2024-05-26","arxiv_id":"2405.16444","repositories_listed":2,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":14,"phrase":"10 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/cacheblend-fast-large-language-model-serving#ran","syntology_url":"https://syntology.ai/paper/2405.16444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16444"}},"official":{"repos":["YaoJiayi/CacheBlend"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-systematic-investigation-of-distilling","slug":"a-systematic-investigation-of-distilling","title":"Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking","date":"2024-05-13","arxiv_id":"2405.07920","repositories_listed":2,"syntology":null},{"url":"/paper/huixiangdou-cr-coreference-resolution-in","slug":"huixiangdou-cr-coreference-resolution-in","title":"Labeling supervised fine-tuning data with the scaling law","date":"2024-05-05","arxiv_id":"2405.02817","repositories_listed":2,"syntology":null},{"url":"/paper/llm-sr-scientific-equation-discovery-via","slug":"llm-sr-scientific-equation-discovery-via","title":"LLM-SR: Scientific Equation Discovery via Programming with Large Language Models","date":"2024-04-29","arxiv_id":"2404.18400","repositories_listed":2,"syntology":null},{"url":"/paper/how-good-are-low-bit-quantized-llama3-models","slug":"how-good-are-low-bit-quantized-llama3-models","title":"An empirical study of LLaMA3 quantization: from LLMs to MLLMs","date":"2024-04-22","arxiv_id":"2404.14047","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/how-good-are-low-bit-quantized-llama3-models#ran","syntology_url":"https://syntology.ai/paper/2404.14047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14047"}},"official":{"repos":["macaronlin/llama3-quantization"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ming-moe-enhancing-medical-multi-task","slug":"ming-moe-enhancing-medical-multi-task","title":"MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts","date":"2024-04-13","arxiv_id":"2404.09027","repositories_listed":2,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ming-moe-enhancing-medical-multi-task#ran","syntology_url":"https://syntology.ai/paper/2404.09027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09027"}},"official":{"repos":["mediabrain-sjtu/ming"],"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":["listed","official"]}}},{"url":"/paper/minigpt4-video-advancing-multimodal-llms-for","slug":"minigpt4-video-advancing-multimodal-llms-for","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","date":"2024-04-04","arxiv_id":"2404.03413","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minigpt4-video-advancing-multimodal-llms-for#ran","syntology_url":"https://syntology.ai/paper/2404.03413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03413"}},"official":{"repos":["Vision-CAIR/MiniGPT4-video"],"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"]}}},{"url":"/paper/nicolay-r-at-semeval-2024-task-3-using-flan","slug":"nicolay-r-at-semeval-2024-task-3-using-flan","title":"nicolay-r at SemEval-2024 Task 3: Using Flan-T5 for Reasoning Emotion Cause in Conversations with Chain-of-Thought on Emotion States","date":"2024-04-04","arxiv_id":"2404.03361","repositories_listed":2,"syntology":null},{"url":"/paper/codebenchgen-creating-scalable-execution","slug":"codebenchgen-creating-scalable-execution","title":"CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks","date":"2024-03-31","arxiv_id":"2404.00566","repositories_listed":2,"syntology":null},{"url":"/paper/extensive-self-contrast-enables-feedback-free","slug":"extensive-self-contrast-enables-feedback-free","title":"Extensive Self-Contrast Enables Feedback-Free Language Model Alignment","date":"2024-03-31","arxiv_id":"2404.00604","repositories_listed":2,"syntology":null},{"url":"/paper/m3d-advancing-3d-medical-image-analysis-with","slug":"m3d-advancing-3d-medical-image-analysis-with","title":"M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models","date":"2024-03-31","arxiv_id":"2404.00578","repositories_listed":2,"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/m3d-advancing-3d-medical-image-analysis-with#ran","syntology_url":"https://syntology.ai/paper/2404.00578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00578"}},"official":{"repos":["baai-dcai/m3d"],"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/tablellm-enabling-tabular-data-manipulation","slug":"tablellm-enabling-tabular-data-manipulation","title":"TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios","date":"2024-03-28","arxiv_id":"2403.19318","repositories_listed":2,"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/tablellm-enabling-tabular-data-manipulation#ran","syntology_url":"https://syntology.ai/paper/2403.19318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19318"}},"official":{"repos":["TableLLM/TableLLM"],"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/llm-agent-operating-system","slug":"llm-agent-operating-system","title":"AIOS: LLM Agent Operating System","date":"2024-03-25","arxiv_id":"2403.16971","repositories_listed":2,"syntology":null},{"url":"/paper/videoagent-long-form-video-understanding-with","slug":"videoagent-long-form-video-understanding-with","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","date":"2024-03-15","arxiv_id":"2403.10517","repositories_listed":2,"syntology":null},{"url":"/paper/decomposing-disease-descriptions-for-enhanced","slug":"decomposing-disease-descriptions-for-enhanced","title":"Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework","date":"2024-03-12","arxiv_id":"2403.07636","repositories_listed":2,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":13,"phrase":"11 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/decomposing-disease-descriptions-for-enhanced#ran","syntology_url":"https://syntology.ai/paper/2403.07636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07636"}},"official":{"repos":["hieuphan33/mavl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/workarena-how-capable-are-web-agents-at","slug":"workarena-how-capable-are-web-agents-at","title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","date":"2024-03-12","arxiv_id":"2403.07718","repositories_listed":2,"syntology":null},{"url":"/paper/ella-equip-diffusion-models-with-llm-for","slug":"ella-equip-diffusion-models-with-llm-for","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","date":"2024-03-08","arxiv_id":"2403.05135","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ella-equip-diffusion-models-with-llm-for#ran","syntology_url":"https://syntology.ai/paper/2403.05135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05135"}},"official":null}},{"url":"/paper/injecagent-benchmarking-indirect-prompt","slug":"injecagent-benchmarking-indirect-prompt","title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","date":"2024-03-05","arxiv_id":"2403.02691","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/injecagent-benchmarking-indirect-prompt#ran","syntology_url":"https://syntology.ai/paper/2403.02691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02691"}},"official":{"repos":["uiuc-kang-lab/injecagent"],"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/towards-democratized-flood-risk-management-an","slug":"towards-democratized-flood-risk-management-an","title":"Towards Democratized Flood Risk Management: An Advanced AI Assistant Enabled by GPT-4 for Enhanced Interpretability and Public Engagement","date":"2024-03-05","arxiv_id":"2403.03188","repositories_listed":2,"syntology":null},{"url":"/paper/wukong-towards-a-scaling-law-for-large-scale","slug":"wukong-towards-a-scaling-law-for-large-scale","title":"Wukong: Towards a Scaling Law for Large-Scale Recommendation","date":"2024-03-04","arxiv_id":"2403.02545","repositories_listed":2,"syntology":null},{"url":"/paper/intactkv-improving-large-language-model","slug":"intactkv-improving-large-language-model","title":"IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact","date":"2024-03-02","arxiv_id":"2403.01241","repositories_listed":2,"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":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) · 1 unverified","sample_list":"/paper/intactkv-improving-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2403.01241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01241"}},"official":{"repos":["ruikangliu/IntactKV"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/learning-to-generate-instruction-tuning","slug":"learning-to-generate-instruction-tuning","title":"Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation","date":"2024-02-28","arxiv_id":"2402.18334","repositories_listed":2,"syntology":null},{"url":"/paper/llm-inference-unveiled-survey-and-roofline","slug":"llm-inference-unveiled-survey-and-roofline","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","date":"2024-02-26","arxiv_id":"2402.16363","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/llm-inference-unveiled-survey-and-roofline#ran","syntology_url":"https://syntology.ai/paper/2402.16363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16363"}},"official":{"repos":["hahnyuan/llm-viewer"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-retrieval-building-an-information","slug":"self-retrieval-building-an-information","title":"Self-Retrieval: End-to-End Information Retrieval with One Large Language Model","date":"2024-02-23","arxiv_id":"2403.00801","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/self-retrieval-building-an-information#ran","syntology_url":"https://syntology.ai/paper/2403.00801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00801"}},"official":{"repos":["icip-cas/selfretrieval","tangqiaoyu/selfretrieval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/criticbench-evaluating-large-language-models","slug":"criticbench-evaluating-large-language-models","title":"CriticEval: Evaluating Large Language Model as Critic","date":"2024-02-21","arxiv_id":"2402.13764","repositories_listed":2,"syntology":null},{"url":"/paper/softmax-probabilities-mostly-predict-large","slug":"softmax-probabilities-mostly-predict-large","title":"Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A","date":"2024-02-20","arxiv_id":"2402.13213","repositories_listed":2,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/softmax-probabilities-mostly-predict-large#ran","syntology_url":"https://syntology.ai/paper/2402.13213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13213"}},"official":{"repos":["bplaut/softmax-probs-predict-llm-correctness","bplaut/llm-calibration-and-correctness-prediction"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/trap-targeted-random-adversarial-prompt","slug":"trap-targeted-random-adversarial-prompt","title":"TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification","date":"2024-02-20","arxiv_id":"2402.12991","repositories_listed":2,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/trap-targeted-random-adversarial-prompt#ran","syntology_url":"https://syntology.ai/paper/2402.12991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12991"}},"official":{"repos":["framartin/trap","parameterlab/trap"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/generation-meets-verification-accelerating","slug":"generation-meets-verification-accelerating","title":"Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding","date":"2024-02-19","arxiv_id":"2402.11809","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generation-meets-verification-accelerating#ran","syntology_url":"https://syntology.ai/paper/2402.11809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11809"}},"official":{"repos":["cteant/space","hiyouga/llama-factory"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/laco-large-language-model-pruning-via-layer","slug":"laco-large-language-model-pruning-via-layer","title":"LaCo: Large Language Model Pruning via Layer Collapse","date":"2024-02-17","arxiv_id":"2402.11187","repositories_listed":2,"syntology":null},{"url":"/paper/generative-representational-instruction","slug":"generative-representational-instruction","title":"Generative Representational Instruction Tuning","date":"2024-02-15","arxiv_id":"2402.09906","repositories_listed":2,"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":5,"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/generative-representational-instruction#ran","syntology_url":"https://syntology.ai/paper/2402.09906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09906"}},"official":{"repos":["contextualai/gritlm"],"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/realm-rag-driven-enhancement-of-multimodal","slug":"realm-rag-driven-enhancement-of-multimodal","title":"REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models","date":"2024-02-10","arxiv_id":"2402.07016","repositories_listed":2,"syntology":null},{"url":"/paper/jailbreaking-attack-against-multimodal-large","slug":"jailbreaking-attack-against-multimodal-large","title":"Jailbreaking Attack against Multimodal Large Language Model","date":"2024-02-04","arxiv_id":"2402.02309","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/jailbreaking-attack-against-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2402.02309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02309"}},"official":{"repos":["abc03570128/jailbreaking-attack-against-multimodal-large-language-model"],"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":["listed","official"]}}},{"url":"/paper/integrating-large-language-models-in-causal","slug":"integrating-large-language-models-in-causal","title":"Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach","date":"2024-02-02","arxiv_id":"2402.01454","repositories_listed":2,"syntology":null},{"url":"/paper/executable-code-actions-elicit-better-llm","slug":"executable-code-actions-elicit-better-llm","title":"Executable Code Actions Elicit Better LLM Agents","date":"2024-02-01","arxiv_id":"2402.01030","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/executable-code-actions-elicit-better-llm#ran","syntology_url":"https://syntology.ai/paper/2402.01030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01030"}},"official":{"repos":["epfllm/megatron-llm","xingyaoww/code-act"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"url":"/paper/large-language-model-evaluation-via-matrix","slug":"large-language-model-evaluation-via-matrix","title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","date":"2024-01-30","arxiv_id":"2401.17139","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-model-evaluation-via-matrix#ran","syntology_url":"https://syntology.ai/paper/2401.17139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17139"}},"official":{"repos":["waltonfuture/Diff-eRank"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/l-autoda-leveraging-large-language-models-for","slug":"l-autoda-leveraging-large-language-models-for","title":"L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks","date":"2024-01-27","arxiv_id":"2401.15335","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/l-autoda-leveraging-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2401.15335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15335"}},"official":{"repos":["pgg3/L-AutoDA"],"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":["listed","official"]}}},{"url":"/paper/tool-lmm-a-large-multi-modal-model-for-tool","slug":"tool-lmm-a-large-multi-modal-model-for-tool","title":"MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning","date":"2024-01-19","arxiv_id":"2401.10727","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tool-lmm-a-large-multi-modal-model-for-tool#ran","syntology_url":"https://syntology.ai/paper/2401.10727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10727"}},"official":{"repos":["mllm-tool/mllm-tool","tool-lmm/tool-lmm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vlogger-make-your-dream-a-vlog","slug":"vlogger-make-your-dream-a-vlog","title":"Vlogger: Make Your Dream A Vlog","date":"2024-01-17","arxiv_id":"2401.09414","repositories_listed":2,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vlogger-make-your-dream-a-vlog#ran","syntology_url":"https://syntology.ai/paper/2401.09414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09414"}},"official":{"repos":["zhuangshaobin/vlogger"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/unlocking-efficiency-in-large-language-model","slug":"unlocking-efficiency-in-large-language-model","title":"Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding","date":"2024-01-15","arxiv_id":"2401.07851","repositories_listed":2,"syntology":null},{"url":"/paper/deepseekmoe-towards-ultimate-expert","slug":"deepseekmoe-towards-ultimate-expert","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","date":"2024-01-11","arxiv_id":"2401.06066","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 3 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) · 1 unverified","sample_list":"/paper/deepseekmoe-towards-ultimate-expert#ran","syntology_url":"https://syntology.ai/paper/2401.06066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06066"}},"official":{"repos":["deepseek-ai/deepseek-moe"],"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":["listed","official"]}}},{"url":"/paper/lego-language-enhanced-multi-modal-grounding","slug":"lego-language-enhanced-multi-modal-grounding","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","date":"2024-01-11","arxiv_id":"2401.06071","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/lego-language-enhanced-multi-modal-grounding#ran","syntology_url":"https://syntology.ai/paper/2401.06071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06071"}},"official":{"repos":["lzw-lzw/groundinggpt","lzw-lzw/lego"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/comparative-analysis-of-llama-and-chatgpt","slug":"comparative-analysis-of-llama-and-chatgpt","title":"Can Large Language Models Understand Molecules?","date":"2024-01-05","arxiv_id":"2402.00024","repositories_listed":2,"syntology":null},{"url":"/paper/differentially-private-low-rank-adaptation-of","slug":"differentially-private-low-rank-adaptation-of","title":"Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning","date":"2023-12-29","arxiv_id":"2312.17493","repositories_listed":2,"syntology":null},{"url":"/paper/challenge-llms-to-reason-about-reasoning-a","slug":"challenge-llms-to-reason-about-reasoning-a","title":"MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation","date":"2023-12-28","arxiv_id":"2312.17080","repositories_listed":2,"syntology":null},{"url":"/paper/tinygpt-v-efficient-multimodal-large-language","slug":"tinygpt-v-efficient-multimodal-large-language","title":"TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones","date":"2023-12-28","arxiv_id":"2312.16862","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tinygpt-v-efficient-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2312.16862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16862"}},"official":{"repos":["dlyuangod/tinygpt-v"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/solar-10-7b-scaling-large-language-models","slug":"solar-10-7b-scaling-large-language-models","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","date":"2023-12-23","arxiv_id":"2312.15166","repositories_listed":2,"syntology":{"n":26,"n_ran":22,"n_constructed":0,"n_ran_checked":17,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":3,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/solar-10-7b-scaling-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2312.15166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15166"}},"official":null}},{"url":"/paper/internvl-scaling-up-vision-foundation-models","slug":"internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"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 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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}},"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/fine-tuning-large-language-models-for-1","slug":"fine-tuning-large-language-models-for-1","title":"Fine-tuning Large Language Models for Adaptive Machine Translation","date":"2023-12-20","arxiv_id":"2312.12740","repositories_listed":2,"syntology":null},{"url":"/paper/powerinfer-fast-large-language-model-serving","slug":"powerinfer-fast-large-language-model-serving","title":"PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU","date":"2023-12-16","arxiv_id":"2312.12456","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/powerinfer-fast-large-language-model-serving#ran","syntology_url":"https://syntology.ai/paper/2312.12456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12456"}},"official":{"repos":["sjtu-ipads/powerinfer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/federated-full-parameter-tuning-of-billion","slug":"federated-full-parameter-tuning-of-billion","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","date":"2023-12-11","arxiv_id":"2312.06353","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 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","sample_list":"/paper/federated-full-parameter-tuning-of-billion#ran","syntology_url":"https://syntology.ai/paper/2312.06353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06353"}},"official":{"repos":["alibaba/federatedscope"],"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":["named_in_paper"]}}},{"url":"/paper/localized-symbolic-knowledge-distillation-for-1","slug":"localized-symbolic-knowledge-distillation-for-1","title":"Localized Symbolic Knowledge Distillation for Visual Commonsense Models","date":"2023-12-08","arxiv_id":"2312.04837","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/localized-symbolic-knowledge-distillation-for-1#ran","syntology_url":"https://syntology.ai/paper/2312.04837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04837"}},"official":{"repos":["jamespark3922/localized-skd","jamespark3922/lskd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/aspen-high-throughput-lora-fine-tuning-of","slug":"aspen-high-throughput-lora-fine-tuning-of","title":"mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs","date":"2023-12-05","arxiv_id":"2312.02515","repositories_listed":2,"syntology":null},{"url":"/paper/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}},"official":{"repos":["renshuhuai-andy/timechat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/critiquellm-scaling-llm-as-critic-for","slug":"critiquellm-scaling-llm-as-critic-for","title":"CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation","date":"2023-11-30","arxiv_id":"2311.18702","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":3,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/critiquellm-scaling-llm-as-critic-for#ran","syntology_url":"https://syntology.ai/paper/2311.18702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18702"}},"official":{"repos":["thu-coai/critiquellm"],"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/taiwan-llm-bridging-the-linguistic-divide","slug":"taiwan-llm-bridging-the-linguistic-divide","title":"Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model","date":"2023-11-29","arxiv_id":"2311.17487","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/taiwan-llm-bridging-the-linguistic-divide#ran","syntology_url":"https://syntology.ai/paper/2311.17487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17487"}},"official":{"repos":["miulab/taiwan-llama","miulab/taiwan-llm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/turkishbertweet-fast-and-reliable-large","slug":"turkishbertweet-fast-and-reliable-large","title":"TurkishBERTweet: Fast and Reliable Large Language Model for Social Media Analysis","date":"2023-11-29","arxiv_id":"2311.18063","repositories_listed":2,"syntology":null},{"url":"/paper/yuan-2-0-a-large-language-model-with","slug":"yuan-2-0-a-large-language-model-with","title":"YUAN 2.0: A Large Language Model with Localized Filtering-based Attention","date":"2023-11-27","arxiv_id":"2311.15786","repositories_listed":2,"syntology":null},{"url":"/paper/finme-a-performance-enhanced-large-language","slug":"finme-a-performance-enhanced-large-language","title":"FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design","date":"2023-11-23","arxiv_id":"2311.13743","repositories_listed":2,"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":0,"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/finme-a-performance-enhanced-large-language#ran","syntology_url":"https://syntology.ai/paper/2311.13743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13743"}},"official":{"repos":["pipiku915/finmem-llm-stocktrading"],"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/extracting-definienda-in-mathematical","slug":"extracting-definienda-in-mathematical","title":"Extracting Definienda in Mathematical Scholarly Articles with Transformers","date":"2023-11-21","arxiv_id":"2311.12448","repositories_listed":2,"syntology":null},{"url":"/paper/towards-natural-language-guided-drones","slug":"towards-natural-language-guided-drones","title":"Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching","date":"2023-11-21","arxiv_id":"2311.12751","repositories_listed":2,"syntology":null},{"url":"/paper/dynapipe-optimizing-multi-task-training","slug":"dynapipe-optimizing-multi-task-training","title":"DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines","date":"2023-11-17","arxiv_id":"2311.10418","repositories_listed":2,"syntology":null},{"url":"/paper/leveraging-llms-for-synthesizing-training","slug":"leveraging-llms-for-synthesizing-training","title":"Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval","date":"2023-11-10","arxiv_id":"2311.05800","repositories_listed":2,"syntology":null},{"url":"/paper/deelm-dependency-enhanced-large-language","slug":"deelm-dependency-enhanced-large-language","title":"BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings","date":"2023-11-09","arxiv_id":"2311.05296","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/deelm-dependency-enhanced-large-language#ran","syntology_url":"https://syntology.ai/paper/2311.05296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05296"}},"official":{"repos":["4ai/bellm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/mplug-owl2-revolutionizing-multi-modal-large","slug":"mplug-owl2-revolutionizing-multi-modal-large","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","date":"2023-11-07","arxiv_id":"2311.04257","repositories_listed":2,"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/mplug-owl2-revolutionizing-multi-modal-large#ran","syntology_url":"https://syntology.ai/paper/2311.04257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04257"}},"official":{"repos":["x-plug/mplug-owl"],"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/large-language-model-can-interpret-latent","slug":"large-language-model-can-interpret-latent","title":"Large Language Model Can Interpret Latent Space of Sequential Recommender","date":"2023-10-31","arxiv_id":"2310.20487","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/large-language-model-can-interpret-latent#ran","syntology_url":"https://syntology.ai/paper/2310.20487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20487"}},"official":{"repos":["yangzhengyi98/recinterpreter"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/lorashear-efficient-large-language-model","slug":"lorashear-efficient-large-language-model","title":"LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery","date":"2023-10-24","arxiv_id":"2310.18356","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 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","sample_list":"/paper/lorashear-efficient-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2310.18356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18356"}},"official":null}},{"url":"/paper/large-language-model-unlearning","slug":"large-language-model-unlearning","title":"Large Language Model Unlearning","date":"2023-10-14","arxiv_id":"2310.10683","repositories_listed":2,"syntology":null},{"url":"/paper/minigpt-v2-large-language-model-as-a-unified","slug":"minigpt-v2-large-language-model-as-a-unified","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","date":"2023-10-14","arxiv_id":"2310.09478","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minigpt-v2-large-language-model-as-a-unified#ran","syntology_url":"https://syntology.ai/paper/2310.09478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09478"}},"official":null}},{"url":"/paper/cachegen-fast-context-loading-for-language","slug":"cachegen-fast-context-loading-for-language","title":"CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving","date":"2023-10-11","arxiv_id":"2310.07240","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cachegen-fast-context-loading-for-language#ran","syntology_url":"https://syntology.ai/paper/2310.07240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07240"}},"official":{"repos":["uchi-jcl/cachegen"],"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"]}}},{"url":"/paper/ferret-refer-and-ground-anything-anywhere-at","slug":"ferret-refer-and-ground-anything-anywhere-at","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","date":"2023-10-11","arxiv_id":"2310.07704","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"phrase":"7 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; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ferret-refer-and-ground-anything-anywhere-at#ran","syntology_url":"https://syntology.ai/paper/2310.07704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07704"}},"official":{"repos":["apple/ml-ferret"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/brainteaser-lateral-thinking-puzzles-for","slug":"brainteaser-lateral-thinking-puzzles-for","title":"BRAINTEASER: Lateral Thinking Puzzles for Large Language Models","date":"2023-10-08","arxiv_id":"2310.05057","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/brainteaser-lateral-thinking-puzzles-for#ran","syntology_url":"https://syntology.ai/paper/2310.05057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05057"}},"official":null}},{"url":"/paper/l2mac-large-language-model-automatic-computer","slug":"l2mac-large-language-model-automatic-computer","title":"L2MAC: Large Language Model Automatic Computer for Extensive Code Generation","date":"2023-10-02","arxiv_id":"2310.02003","repositories_listed":2,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"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) · 4 unverified","sample_list":"/paper/l2mac-large-language-model-automatic-computer#ran","syntology_url":"https://syntology.ai/paper/2310.02003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02003"}},"official":{"repos":["samholt/l2mac","vanderschaarlab/l2mac"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/qwen-technical-report","slug":"qwen-technical-report","title":"Qwen Technical Report","date":"2023-09-28","arxiv_id":"2309.16609","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/qwen-technical-report#ran","syntology_url":"https://syntology.ai/paper/2309.16609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16609"}},"official":{"repos":["QwenLM/Qwen-7B","qwenlm/qwen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rllte-long-term-evolution-project-of","slug":"rllte-long-term-evolution-project-of","title":"RLLTE: Long-Term Evolution Project of Reinforcement Learning","date":"2023-09-28","arxiv_id":"2309.16382","repositories_listed":2,"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/rllte-long-term-evolution-project-of#ran","syntology_url":"https://syntology.ai/paper/2309.16382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16382"}},"official":{"repos":["RLE-Foundation/rllte"],"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/angle-optimized-text-embeddings","slug":"angle-optimized-text-embeddings","title":"AnglE-optimized Text Embeddings","date":"2023-09-22","arxiv_id":"2309.12871","repositories_listed":2,"syntology":null},{"url":"/paper/disc-lawllm-fine-tuning-large-language-models","slug":"disc-lawllm-fine-tuning-large-language-models","title":"DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services","date":"2023-09-20","arxiv_id":"2309.11325","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/disc-lawllm-fine-tuning-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2309.11325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.11325"}},"official":{"repos":["fudandisc/disc-lawllm"],"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":["listed","official"]}}},{"url":"/paper/large-language-models-can-accurately-predict","slug":"large-language-models-can-accurately-predict","title":"Large language models can accurately predict searcher preferences","date":"2023-09-19","arxiv_id":"2309.10621","repositories_listed":2,"syntology":null},{"url":"/paper/speaker-attribution-in-german-parliamentary","slug":"speaker-attribution-in-german-parliamentary","title":"Speaker attribution in German parliamentary debates with QLoRA-adapted large language models","date":"2023-09-18","arxiv_id":"2309.09902","repositories_listed":2,"syntology":null},{"url":"/paper/fedjudge-federated-legal-large-language-model","slug":"fedjudge-federated-legal-large-language-model","title":"FedJudge: Federated Legal Large Language Model","date":"2023-09-15","arxiv_id":"2309.08173","repositories_listed":2,"syntology":null},{"url":"/paper/sib-200-a-simple-inclusive-and-big-evaluation","slug":"sib-200-a-simple-inclusive-and-big-evaluation","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","date":"2023-09-14","arxiv_id":"2309.07445","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sib-200-a-simple-inclusive-and-big-evaluation#ran","syntology_url":"https://syntology.ai/paper/2309.07445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07445"}},"official":{"repos":["dadelani/sib-200"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-the-efficacy-of-supervised","slug":"evaluating-the-efficacy-of-supervised","title":"Supervised Learning and Large Language Model Benchmarks on Mental Health Datasets: Cognitive Distortions and Suicidal Risks in Chinese Social Media","date":"2023-09-07","arxiv_id":"2309.03564","repositories_listed":2,"syntology":null},{"url":"/paper/isr-llm-iterative-self-refined-large-language","slug":"isr-llm-iterative-self-refined-large-language","title":"ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning","date":"2023-08-26","arxiv_id":"2308.13724","repositories_listed":2,"syntology":null}],"record_sha256":"c46f538d5386a806e54dea4f1db621c74649ce15543aa3d147d8f873053744d7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}