{"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/10","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":10,"pages_in_order":61,"rows_per_page":100,"rows":[901,1000],"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/papers/9","next":"/task/large-language-model/papers/11","papers":[{"url":"/paper/online-intrinsic-rewards-for-decision-making","slug":"online-intrinsic-rewards-for-decision-making","title":"Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback","date":"2024-10-30","arxiv_id":"2410.23022","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/online-intrinsic-rewards-for-decision-making#ran","syntology_url":"https://syntology.ai/paper/2410.23022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23022"}},"official":{"repos":["facebookresearch/oni"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/real-time-personalization-for-llm-based","slug":"real-time-personalization-for-llm-based","title":"Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning","date":"2024-10-30","arxiv_id":"2410.23136","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":7,"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) · 1 unverified","sample_list":"/paper/real-time-personalization-for-llm-based#ran","syntology_url":"https://syntology.ai/paper/2410.23136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23136"}},"official":{"repos":["ym689/rec_icl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/online-detecting-llm-generated-texts-via","slug":"online-detecting-llm-generated-texts-via","title":"Online Detecting LLM-Generated Texts via Sequential Hypothesis Testing by Betting","date":"2024-10-29","arxiv_id":"2410.22318","repositories_listed":1,"syntology":null},{"url":"/paper/protecting-privacy-in-multimodal-large","slug":"protecting-privacy-in-multimodal-large","title":"Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench","date":"2024-10-29","arxiv_id":"2410.22108","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/protecting-privacy-in-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2410.22108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22108"}},"official":{"repos":["franciscoliu/MLLMU-Bench"],"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/rare-to-frequent-unlocking-compositional","slug":"rare-to-frequent-unlocking-compositional","title":"Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance","date":"2024-10-29","arxiv_id":"2410.22376","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rare-to-frequent-unlocking-compositional#ran","syntology_url":"https://syntology.ai/paper/2410.22376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22376"}},"official":{"repos":["krafton-ai/rare-to-frequent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/sg-bench-evaluating-llm-safety-generalization","slug":"sg-bench-evaluating-llm-safety-generalization","title":"SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types","date":"2024-10-29","arxiv_id":"2410.21965","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sg-bench-evaluating-llm-safety-generalization#ran","syntology_url":"https://syntology.ai/paper/2410.21965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21965"}},"official":{"repos":["MurrayTom/SG-Bench"],"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/large-language-model-guided-prediction-toward","slug":"large-language-model-guided-prediction-toward","title":"Large Language Model-Guided Prediction Toward Quantum Materials Synthesis","date":"2024-10-28","arxiv_id":"2410.20976","repositories_listed":1,"syntology":null},{"url":"/paper/llmcbench-benchmarking-large-language-model","slug":"llmcbench-benchmarking-large-language-model","title":"LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment","date":"2024-10-28","arxiv_id":"2410.21352","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"14 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/llmcbench-benchmarking-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.21352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21352"}},"official":{"repos":["aboveparadise/llmcbench"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/implementation-and-application-of-an","slug":"implementation-and-application-of-an","title":"Implementation and Application of an Intelligibility Protocol for Interaction with an LLM","date":"2024-10-27","arxiv_id":"2410.20600","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/implementation-and-application-of-an#ran","syntology_url":"https://syntology.ai/paper/2410.20600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20600"}},"official":{"repos":["karannb/interact"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sequential-large-language-model-based-hyper","slug":"sequential-large-language-model-based-hyper","title":"Sequential Large Language Model-Based Hyper-parameter Optimization","date":"2024-10-27","arxiv_id":"2410.20302","repositories_listed":1,"syntology":null},{"url":"/paper/trajagent-an-agent-framework-for-unified","slug":"trajagent-an-agent-framework-for-unified","title":"TrajAgent: An Agent Framework for Unified Trajectory Modelling","date":"2024-10-27","arxiv_id":"2410.20445","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/trajagent-an-agent-framework-for-unified#ran","syntology_url":"https://syntology.ai/paper/2410.20445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20445"}},"official":{"repos":["tsinghua-fib-lab/trajagent"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/flow-a-feedback-loop-framework-for","slug":"flow-a-feedback-loop-framework-for","title":"Agentic Feedback Loop Modeling Improves Recommendation and User Simulation","date":"2024-10-26","arxiv_id":"2410.20027","repositories_listed":1,"syntology":null},{"url":"/paper/coat-compressing-optimizer-states-and","slug":"coat-compressing-optimizer-states-and","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","date":"2024-10-25","arxiv_id":"2410.19313","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/coat-compressing-optimizer-states-and#ran","syntology_url":"https://syntology.ai/paper/2410.19313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19313"}},"official":{"repos":["nvlabs/coat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/gcoder-improving-large-language-model-for","slug":"gcoder-improving-large-language-model-for","title":"GCoder: Improving Large Language Model for Generalized Graph Problem Solving","date":"2024-10-24","arxiv_id":"2410.19084","repositories_listed":1,"syntology":null},{"url":"/paper/asynchronous-rlhf-faster-and-more-efficient","slug":"asynchronous-rlhf-faster-and-more-efficient","title":"Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models","date":"2024-10-23","arxiv_id":"2410.18252","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/asynchronous-rlhf-faster-and-more-efficient#ran","syntology_url":"https://syntology.ai/paper/2410.18252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18252"}},"official":{"repos":["mnoukhov/async_rlhf"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/omniflatten-an-end-to-end-gpt-model-for","slug":"omniflatten-an-end-to-end-gpt-model-for","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","date":"2024-10-23","arxiv_id":"2410.17799","repositories_listed":1,"syntology":null},{"url":"/paper/adsorb-agent-autonomous-identification-of","slug":"adsorb-agent-autonomous-identification-of","title":"Adsorb-Agent: Autonomous Identification of Stable Adsorption Configurations via Large Language Model Agent","date":"2024-10-22","arxiv_id":"2410.16658","repositories_listed":1,"syntology":null},{"url":"/paper/automated-spinal-mri-labelling-from-reports","slug":"automated-spinal-mri-labelling-from-reports","title":"Automated Spinal MRI Labelling from Reports Using a Large Language Model","date":"2024-10-22","arxiv_id":"2410.17235","repositories_listed":1,"syntology":null},{"url":"/paper/dnahlm-dna-sequence-and-human-language-mixed","slug":"dnahlm-dna-sequence-and-human-language-mixed","title":"DNAHLM -- DNA sequence and Human Language mixed large language Model","date":"2024-10-22","arxiv_id":"2410.16917","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-possibilities-of-ai-powered-legal","slug":"exploring-possibilities-of-ai-powered-legal","title":"Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling","date":"2024-10-22","arxiv_id":"2410.17210","repositories_listed":1,"syntology":null},{"url":"/paper/math-neurosurgery-isolating-language-models","slug":"math-neurosurgery-isolating-language-models","title":"Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes","date":"2024-10-22","arxiv_id":"2410.16930","repositories_listed":1,"syntology":null},{"url":"/paper/meaning-typed-prompting-a-technique-for","slug":"meaning-typed-prompting-a-technique-for","title":"Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output Generation","date":"2024-10-22","arxiv_id":"2410.18146","repositories_listed":1,"syntology":null},{"url":"/paper/navigating-noisy-feedback-enhancing","slug":"navigating-noisy-feedback-enhancing","title":"Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models","date":"2024-10-22","arxiv_id":"2410.17389","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/navigating-noisy-feedback-enhancing#ran","syntology_url":"https://syntology.ai/paper/2410.17389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17389"}},"official":{"repos":["sy-shi/RLAIF_ScoreDiff"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/satori-towards-proactive-ar-assistant-with","slug":"satori-towards-proactive-ar-assistant-with","title":"Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling","date":"2024-10-22","arxiv_id":"2410.16668","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-influence-and-fact-tracing-for-large","slug":"scalable-influence-and-fact-tracing-for-large","title":"Scalable Influence and Fact Tracing for Large Language Model Pretraining","date":"2024-10-22","arxiv_id":"2410.17413","repositories_listed":1,"syntology":null},{"url":"/paper/a-realistic-threat-model-for-large-language","slug":"a-realistic-threat-model-for-large-language","title":"A Realistic Threat Model for Large Language Model Jailbreaks","date":"2024-10-21","arxiv_id":"2410.16222","repositories_listed":1,"syntology":null},{"url":"/paper/autotrain-no-code-training-for-state-of-the","slug":"autotrain-no-code-training-for-state-of-the","title":"AutoTrain: No-code training for state-of-the-art models","date":"2024-10-21","arxiv_id":"2410.15735","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-and-data-augmentation-for","slug":"deep-learning-and-data-augmentation-for","title":"Deep Learning and Data Augmentation for Detecting Self-Admitted Technical Debt","date":"2024-10-21","arxiv_id":"2410.15804","repositories_listed":1,"syntology":null},{"url":"/paper/katzbot-revolutionizing-academic-chatbot-for","slug":"katzbot-revolutionizing-academic-chatbot-for","title":"KatzBot: Revolutionizing Academic Chatbot for Enhanced Communication","date":"2024-10-21","arxiv_id":"2410.16385","repositories_listed":1,"syntology":null},{"url":"/paper/residual-vector-quantization-for-kv-cache","slug":"residual-vector-quantization-for-kv-cache","title":"Residual vector quantization for KV cache compression in large language model","date":"2024-10-21","arxiv_id":"2410.15704","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/residual-vector-quantization-for-kv-cache#ran","syntology_url":"https://syntology.ai/paper/2410.15704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15704"}},"official":{"repos":["iankur/vqllm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spa-bench-a-comprehensive-benchmark-for","slug":"spa-bench-a-comprehensive-benchmark-for","title":"SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation","date":"2024-10-19","arxiv_id":"2410.15164","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/spa-bench-a-comprehensive-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2410.15164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15164"}},"official":{"repos":["ai-agents-2030/SPA-Bench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/paths-over-graph-knowledge-graph-enpowered#ran","syntology_url":"https://syntology.ai/paper/2410.14211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14211"}},"official":null}},{"url":"/paper/sprig-improving-large-language-model","slug":"sprig-improving-large-language-model","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","date":"2024-10-18","arxiv_id":"2410.14826","repositories_listed":1,"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sprig-improving-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.14826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14826"}},"official":{"repos":["orange0629/prompting"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/tell-me-what-i-need-to-know-exploring-llm","slug":"tell-me-what-i-need-to-know-exploring-llm","title":"Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization","date":"2024-10-18","arxiv_id":"2410.14545","repositories_listed":1,"syntology":null},{"url":"/paper/aixcoder-7b-a-lightweight-and-effective-large","slug":"aixcoder-7b-a-lightweight-and-effective-large","title":"aiXcoder-7B: A Lightweight and Effective Large Language Model for Code Processing","date":"2024-10-17","arxiv_id":"2410.13187","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aixcoder-7b-a-lightweight-and-effective-large#ran","syntology_url":"https://syntology.ai/paper/2410.13187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13187"}},"official":{"repos":["aixcoder-plugin/aixcoder-7b"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/detecting-ai-generated-texts-in-cross-domains","slug":"detecting-ai-generated-texts-in-cross-domains","title":"Detecting AI-Generated Texts in Cross-Domains","date":"2024-10-17","arxiv_id":"2410.13966","repositories_listed":1,"syntology":null},{"url":"/paper/fire-fact-checking-with-iterative-retrieval","slug":"fire-fact-checking-with-iterative-retrieval","title":"FIRE: Fact-checking with Iterative Retrieval and Verification","date":"2024-10-17","arxiv_id":"2411.00784","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fire-fact-checking-with-iterative-retrieval#ran","syntology_url":"https://syntology.ai/paper/2411.00784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00784"}},"official":{"repos":["mbzuai-nlp/fire"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/help-me-identify-is-an-llm-vqa-system-all-we","slug":"help-me-identify-is-an-llm-vqa-system-all-we","title":"Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?","date":"2024-10-17","arxiv_id":"2410.13651","repositories_listed":1,"syntology":null},{"url":"/paper/medinst-meta-dataset-of-biomedical","slug":"medinst-meta-dataset-of-biomedical","title":"MedINST: Meta Dataset of Biomedical Instructions","date":"2024-10-17","arxiv_id":"2410.13458","repositories_listed":1,"syntology":null},{"url":"/paper/mirage-bench-automatic-multilingual-benchmark","slug":"mirage-bench-automatic-multilingual-benchmark","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","date":"2024-10-17","arxiv_id":"2410.13716","repositories_listed":1,"syntology":null},{"url":"/paper/moba-a-two-level-agent-system-for-efficient","slug":"moba-a-two-level-agent-system-for-efficient","title":"MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation","date":"2024-10-17","arxiv_id":"2410.13757","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-role-of-attention-heads-in-large","slug":"on-the-role-of-attention-heads-in-large","title":"On the Role of Attention Heads in Large Language Model Safety","date":"2024-10-17","arxiv_id":"2410.13708","repositories_listed":1,"syntology":{"n":24,"n_ran":16,"n_constructed":0,"n_ran_checked":8,"n_instrument":8,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":24,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/on-the-role-of-attention-heads-in-large#ran","syntology_url":"https://syntology.ai/paper/2410.13708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13708"}},"official":{"repos":["ydyjya/safetyheadattribution"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/sbi-rag-enhancing-math-word-problem-solving","slug":"sbi-rag-enhancing-math-word-problem-solving","title":"SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation","date":"2024-10-17","arxiv_id":"2410.13293","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-role-of-llms-in-multimodal","slug":"understanding-the-role-of-llms-in-multimodal","title":"Understanding the Role of LLMs in Multimodal Evaluation Benchmarks","date":"2024-10-16","arxiv_id":"2410.12329","repositories_listed":1,"syntology":null},{"url":"/paper/a-framework-for-adapting-human-robot","slug":"a-framework-for-adapting-human-robot","title":"A Framework for Adapting Human-Robot Interaction to Diverse User Groups","date":"2024-10-15","arxiv_id":"2410.11377","repositories_listed":1,"syntology":null},{"url":"/paper/automatically-generating-visual-hallucination","slug":"automatically-generating-visual-hallucination","title":"Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models","date":"2024-10-15","arxiv_id":"2410.11242","repositories_listed":1,"syntology":null},{"url":"/paper/de-jargonizing-science-for-journalists-with","slug":"de-jargonizing-science-for-journalists-with","title":"De-jargonizing Science for Journalists with GPT-4: A Pilot Study","date":"2024-10-15","arxiv_id":"2410.12069","repositories_listed":1,"syntology":null},{"url":"/paper/gavamoe-gaussian-variational-gated-mixture-of","slug":"gavamoe-gaussian-variational-gated-mixture-of","title":"GaVaMoE: Gaussian-Variational Gated Mixture of Experts for Explainable Recommendation","date":"2024-10-15","arxiv_id":"2410.11841","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-llm-embeddings-for-cross-dataset","slug":"leveraging-llm-embeddings-for-cross-dataset","title":"Leveraging LLM Embeddings for Cross Dataset Label Alignment and Zero Shot Music Emotion Prediction","date":"2024-10-15","arxiv_id":"2410.11522","repositories_listed":1,"syntology":null},{"url":"/paper/search-engines-in-an-ai-era-the-false-promise","slug":"search-engines-in-an-ai-era-the-false-promise","title":"Search Engines in an AI Era: The False Promise of Factual and Verifiable Source-Cited Responses","date":"2024-10-15","arxiv_id":"2410.22349","repositories_listed":1,"syntology":null},{"url":"/paper/weatherdg-llm-assisted-procedural-weather","slug":"weatherdg-llm-assisted-procedural-weather","title":"WeatherDG: LLM-assisted Diffusion Model for Procedural Weather Generation in Domain-Generalized Semantic Segmentation","date":"2024-10-15","arxiv_id":"2410.12075","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-leverage-demonstration-data-in","slug":"how-to-leverage-demonstration-data-in","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","date":"2024-10-14","arxiv_id":"2410.10093","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/how-to-leverage-demonstration-data-in#ran","syntology_url":"https://syntology.ai/paper/2410.10093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10093"}},"official":{"repos":["tengxiao1/gsil"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-evaluation-via-matrix-1","slug":"large-language-model-evaluation-via-matrix-1","title":"Large Language Model Evaluation via Matrix Nuclear-Norm","date":"2024-10-14","arxiv_id":"2410.10672","repositories_listed":1,"syntology":null},{"url":"/paper/longmemeval-benchmarking-chat-assistants-on","slug":"longmemeval-benchmarking-chat-assistants-on","title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","date":"2024-10-14","arxiv_id":"2410.10813","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/longmemeval-benchmarking-chat-assistants-on#ran","syntology_url":"https://syntology.ai/paper/2410.10813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10813"}},"official":{"repos":["xiaowu0162/longmemeval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/hardmath-a-benchmark-dataset-for-challenging","slug":"hardmath-a-benchmark-dataset-for-challenging","title":"HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics","date":"2024-10-13","arxiv_id":"2410.09988","repositories_listed":1,"syntology":null},{"url":"/paper/drcap-decoding-clap-latents-with-retrieval","slug":"drcap-decoding-clap-latents-with-retrieval","title":"DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning","date":"2024-10-12","arxiv_id":"2410.09472","repositories_listed":1,"syntology":null},{"url":"/paper/linked-eliciting-filtering-and-integrating","slug":"linked-eliciting-filtering-and-integrating","title":"LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning","date":"2024-10-12","arxiv_id":"2410.09541","repositories_listed":1,"syntology":null},{"url":"/paper/can-a-large-language-model-be-a-gaslighter","slug":"can-a-large-language-model-be-a-gaslighter","title":"Can a large language model be a gaslighter?","date":"2024-10-11","arxiv_id":"2410.09181","repositories_listed":1,"syntology":null},{"url":"/paper/enterprise-benchmarks-for-large-language","slug":"enterprise-benchmarks-for-large-language","title":"Enterprise Benchmarks for Large Language Model Evaluation","date":"2024-10-11","arxiv_id":"2410.12857","repositories_listed":1,"syntology":null},{"url":"/paper/hespi-a-pipeline-for-automatically-detecting","slug":"hespi-a-pipeline-for-automatically-detecting","title":"Hespi: A pipeline for automatically detecting information from hebarium specimen sheets","date":"2024-10-11","arxiv_id":"2410.08740","repositories_listed":1,"syntology":null},{"url":"/paper/pear-a-robust-and-flexible-automation","slug":"pear-a-robust-and-flexible-automation","title":"PEAR: A Robust and Flexible Automation Framework for Ptychography Enabled by Multiple Large Language Model Agents","date":"2024-10-11","arxiv_id":"2410.09034","repositories_listed":1,"syntology":null},{"url":"/paper/poisonbench-assessing-large-language-model","slug":"poisonbench-assessing-large-language-model","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","date":"2024-10-11","arxiv_id":"2410.08811","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/poisonbench-assessing-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.08811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08811"}},"official":{"repos":["tingchenfu/poisonbench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/retraining-free-merging-of-sparse-mixture-of","slug":"retraining-free-merging-of-sparse-mixture-of","title":"Retraining-Free Merging of Sparse MoE via Hierarchical Clustering","date":"2024-10-11","arxiv_id":"2410.08589","repositories_listed":1,"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":8,"n_instrument":7,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/retraining-free-merging-of-sparse-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2410.08589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08589"}},"official":{"repos":["wazenmai/hc-smoe"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/divide-and-translate-compositional-first","slug":"divide-and-translate-compositional-first","title":"Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning","date":"2024-10-10","arxiv_id":"2410.08047","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/divide-and-translate-compositional-first#ran","syntology_url":"https://syntology.ai/paper/2410.08047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08047"}},"official":{"repos":["Hyun-Ryu/clover"],"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/onenet-a-fine-tuning-free-framework-for-few","slug":"onenet-a-fine-tuning-free-framework-for-few","title":"OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting","date":"2024-10-10","arxiv_id":"2410.07549","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/onenet-a-fine-tuning-free-framework-for-few#ran","syntology_url":"https://syntology.ai/paper/2410.07549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07549"}},"official":{"repos":["laquabe/OneNet"],"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/plug-and-play-performance-estimation-for-llm","slug":"plug-and-play-performance-estimation-for-llm","title":"Plug-and-Play Performance Estimation for LLM Services without Relying on Labeled Data","date":"2024-10-10","arxiv_id":"2410.07737","repositories_listed":1,"syntology":null},{"url":"/paper/towards-next-generation-llm-based-recommender","slug":"towards-next-generation-llm-based-recommender","title":"Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond","date":"2024-10-10","arxiv_id":"2410.19744","repositories_listed":1,"syntology":null},{"url":"/paper/auditwen-an-open-source-large-language-model","slug":"auditwen-an-open-source-large-language-model","title":"AuditWen:An Open-Source Large Language Model for Audit","date":"2024-10-09","arxiv_id":"2410.10873","repositories_listed":1,"syntology":null},{"url":"/paper/i-want-to-break-free-anti-social-behavior-and","slug":"i-want-to-break-free-anti-social-behavior-and","title":"I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy","date":"2024-10-09","arxiv_id":"2410.07109","repositories_listed":1,"syntology":null},{"url":"/paper/tinyemo-scaling-down-emotional-reasoning-via","slug":"tinyemo-scaling-down-emotional-reasoning-via","title":"TinyEmo: Scaling down Emotional Reasoning via Metric Projection","date":"2024-10-09","arxiv_id":"2410.07062","repositories_listed":1,"syntology":null},{"url":"/paper/pdf-wukong-a-large-multimodal-model-for","slug":"pdf-wukong-a-large-multimodal-model-for","title":"PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling","date":"2024-10-08","arxiv_id":"2410.05970","repositories_listed":1,"syntology":null},{"url":"/paper/chatvis-automating-scientific-visualization","slug":"chatvis-automating-scientific-visualization","title":"ChatVis: Automating Scientific Visualization with a Large Language Model","date":"2024-10-07","arxiv_id":"2410.11863","repositories_listed":1,"syntology":null},{"url":"/paper/data-advisor-dynamic-data-curation-for-safety","slug":"data-advisor-dynamic-data-curation-for-safety","title":"Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models","date":"2024-10-07","arxiv_id":"2410.05269","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/data-advisor-dynamic-data-curation-for-safety#ran","syntology_url":"https://syntology.ai/paper/2410.05269","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05269"}},"official":{"repos":["feiwang96/Data-Advisor"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-inference-for-large-language-model","slug":"efficient-inference-for-large-language-model","title":"Efficient Inference for Large Language Model-based Generative Recommendation","date":"2024-10-07","arxiv_id":"2410.05165","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":1,"n_ran_checked":7,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"8 ran (of which 1 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) · 4 unverified","sample_list":"/paper/efficient-inference-for-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.05165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05165"}},"official":{"repos":["linxyhaha/atspeed"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-modality-prior-induced","slug":"mitigating-modality-prior-induced","title":"Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality","date":"2024-10-07","arxiv_id":"2410.04780","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mitigating-modality-prior-induced#ran","syntology_url":"https://syntology.ai/paper/2410.04780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04780"}},"official":{"repos":["the-martyr/causalmm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-machine-translation-system-for-lezgian","slug":"neural-machine-translation-system-for-lezgian","title":"Neural machine translation system for Lezgian, Russian and Azerbaijani languages","date":"2024-10-07","arxiv_id":"2410.05472","repositories_listed":1,"syntology":null},{"url":"/paper/synthesizing-interpretable-control-policies","slug":"synthesizing-interpretable-control-policies","title":"Synthesizing Interpretable Control Policies through Large Language Model Guided Search","date":"2024-10-07","arxiv_id":"2410.05406","repositories_listed":1,"syntology":null},{"url":"/paper/gensim-a-general-social-simulation-platform","slug":"gensim-a-general-social-simulation-platform","title":"GenSim: A General Social Simulation Platform with Large Language Model based Agents","date":"2024-10-06","arxiv_id":"2410.04360","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"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) · 3 unverified","sample_list":"/paper/gensim-a-general-social-simulation-platform#ran","syntology_url":"https://syntology.ai/paper/2410.04360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04360"}},"official":{"repos":["TangJiakai/GenSim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-inference-acceleration-a","slug":"large-language-model-inference-acceleration-a","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","date":"2024-10-06","arxiv_id":"2410.04466","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-reliability-of-large-language-models","slug":"on-the-reliability-of-large-language-models","title":"On the Reliability of Large Language Models to Misinformed and Demographically-Informed Prompts","date":"2024-10-06","arxiv_id":"2410.10850","repositories_listed":1,"syntology":null},{"url":"/paper/enriching-music-descriptions-with-a-finetuned","slug":"enriching-music-descriptions-with-a-finetuned","title":"Enriching Music Descriptions with a Finetuned-LLM and Metadata for Text-to-Music Retrieval","date":"2024-10-04","arxiv_id":"2410.03264","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enriching-music-descriptions-with-a-finetuned#ran","syntology_url":"https://syntology.ai/paper/2410.03264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03264"}},"official":{"repos":["seungheondoh/music-text-representation-pp"],"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/leveraging-social-determinants-of-health-in","slug":"leveraging-social-determinants-of-health-in","title":"Leveraging Social Determinants of Health in Alzheimer's Research Using LLM-Augmented Literature Mining and Knowledge Graphs","date":"2024-10-04","arxiv_id":"2410.09080","repositories_listed":1,"syntology":null},{"url":"/paper/one2set-large-language-model-best-partners","slug":"one2set-large-language-model-best-partners","title":"One2set + Large Language Model: Best Partners for Keyphrase Generation","date":"2024-10-04","arxiv_id":"2410.03421","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/one2set-large-language-model-best-partners#ran","syntology_url":"https://syntology.ai/paper/2410.03421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03421"}},"official":{"repos":["deeplearnxmu/kpg-setllm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/searching-for-best-practices-in-medical","slug":"searching-for-best-practices-in-medical","title":"Searching for Best Practices in Medical Transcription with Large Language Model","date":"2024-10-04","arxiv_id":"2410.03797","repositories_listed":1,"syntology":null},{"url":"/paper/you-know-what-i-m-saying-jailbreak-attack-via","slug":"you-know-what-i-m-saying-jailbreak-attack-via","title":"You Know What I'm Saying: Jailbreak Attack via Implicit Reference","date":"2024-10-04","arxiv_id":"2410.03857","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/you-know-what-i-m-saying-jailbreak-attack-via#ran","syntology_url":"https://syntology.ai/paper/2410.03857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03857"}},"official":{"repos":["lucas-ty/llm_implicit_reference"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-dutch-financial-large-language-model","slug":"a-dutch-financial-large-language-model","title":"A Dutch Financial Large Language Model","date":"2024-10-03","arxiv_id":"2410.12835","repositories_listed":1,"syntology":null},{"url":"/paper/choices-are-more-important-than-efforts-llm","slug":"choices-are-more-important-than-efforts-llm","title":"Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration","date":"2024-10-03","arxiv_id":"2410.02511","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/choices-are-more-important-than-efforts-llm#ran","syntology_url":"https://syntology.ai/paper/2410.02511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02511"}},"official":{"repos":["hijkzzz/pymarl2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sca-highly-efficient-semantic-consistent","slug":"sca-highly-efficient-semantic-consistent","title":"SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM Inversion","date":"2024-10-03","arxiv_id":"2410.02240","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-deductive-coding-in-discourse","slug":"automatic-deductive-coding-in-discourse","title":"Automatic deductive coding in discourse analysis: an application of large language models in learning analytics","date":"2024-10-02","arxiv_id":"2410.01240","repositories_listed":1,"syntology":null},{"url":"/paper/basis-sharing-cross-layer-parameter-sharing","slug":"basis-sharing-cross-layer-parameter-sharing","title":"Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression","date":"2024-10-02","arxiv_id":"2410.03765","repositories_listed":1,"syntology":null},{"url":"/paper/elaborative-subtopic-query-reformulation-for","slug":"elaborative-subtopic-query-reformulation-for","title":"Elaborative Subtopic Query Reformulation for Broad and Indirect Queries in Travel Destination Recommendation","date":"2024-10-02","arxiv_id":"2410.01598","repositories_listed":1,"syntology":null},{"url":"/paper/generate-then-refine-data-augmentation-for","slug":"generate-then-refine-data-augmentation-for","title":"Generate then Refine: Data Augmentation for Zero-shot Intent Detection","date":"2024-10-02","arxiv_id":"2410.01953","repositories_listed":1,"syntology":null},{"url":"/paper/locret-enhancing-eviction-in-long-context-llm","slug":"locret-enhancing-eviction-in-long-context-llm","title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","date":"2024-10-02","arxiv_id":"2410.01805","repositories_listed":1,"syntology":null},{"url":"/paper/mind-scramble-unveiling-large-language-model","slug":"mind-scramble-unveiling-large-language-model","title":"Mind Scramble: Unveiling Large Language Model Psychology Via Typoglycemia","date":"2024-10-02","arxiv_id":"2410.01677","repositories_listed":1,"syntology":null},{"url":"/paper/openmathinstruct-2-accelerating-ai-for-math","slug":"openmathinstruct-2-accelerating-ai-for-math","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","date":"2024-10-02","arxiv_id":"2410.01560","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/openmathinstruct-2-accelerating-ai-for-math#ran","syntology_url":"https://syntology.ai/paper/2410.01560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01560"}},"official":null}},{"url":"/paper/typedthinker-typed-thinking-improves-large","slug":"typedthinker-typed-thinking-improves-large","title":"TypedThinker: Typed Thinking Improves Large Language Model Reasoning","date":"2024-10-02","arxiv_id":"2410.01952","repositories_listed":1,"syntology":null},{"url":"/paper/empowering-large-language-model-for-continual","slug":"empowering-large-language-model-for-continual","title":"Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting","date":"2024-10-01","arxiv_id":"2410.00771","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-empty-spaces-human-in-the-loop-data","slug":"exploring-empty-spaces-human-in-the-loop-data","title":"Exploring Empty Spaces: Human-in-the-Loop Data Augmentation","date":"2024-10-01","arxiv_id":"2410.01088","repositories_listed":1,"syntology":null},{"url":"/paper/layerkv-optimizing-large-language-model","slug":"layerkv-optimizing-large-language-model","title":"LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management","date":"2024-10-01","arxiv_id":"2410.00428","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":5,"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) · 5 unverified","sample_list":"/paper/layerkv-optimizing-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.00428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00428"}},"official":null}},{"url":"/paper/pclgpt-a-large-language-model-for-patronizing","slug":"pclgpt-a-large-language-model-for-patronizing","title":"PclGPT: A Large Language Model for Patronizing and Condescending Language Detection","date":"2024-10-01","arxiv_id":"2410.00361","repositories_listed":1,"syntology":null}],"record_sha256":"5a8aa6a2a74011faac756013a1c87831026c7931cea21d3e6bd71f6157f4a4d7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}