{"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/9","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":9,"pages_in_order":61,"rows_per_page":100,"rows":[801,900],"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/8","next":"/task/large-language-model/papers/10","papers":[{"url":"/paper/learning-to-verify-summary-facts-with-fine","slug":"learning-to-verify-summary-facts-with-fine","title":"Learning to Verify Summary Facts with Fine-Grained LLM Feedback","date":"2024-12-14","arxiv_id":"2412.10689","repositories_listed":1,"syntology":null},{"url":"/paper/b-vllm-a-vision-large-language-model-with","slug":"b-vllm-a-vision-large-language-model-with","title":"B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens","date":"2024-12-13","arxiv_id":"2412.09919","repositories_listed":1,"syntology":null},{"url":"/paper/from-allies-to-adversaries-manipulating-llm","slug":"from-allies-to-adversaries-manipulating-llm","title":"From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection","date":"2024-12-13","arxiv_id":"2412.10198","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/from-allies-to-adversaries-manipulating-llm#ran","syntology_url":"https://syntology.ai/paper/2412.10198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10198"}},"official":{"repos":["anonymous-lgtm/toolcommander"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/you-name-it-i-run-it-an-llm-agent-to-execute","slug":"you-name-it-i-run-it-an-llm-agent-to-execute","title":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","date":"2024-12-13","arxiv_id":"2412.10133","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/you-name-it-i-run-it-an-llm-agent-to-execute#ran","syntology_url":"https://syntology.ai/paper/2412.10133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10133"}},"official":{"repos":["sola-st/executionagent"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/atprompt-textual-prompt-learning-with","slug":"atprompt-textual-prompt-learning-with","title":"ATPrompt: Textual Prompt Learning with Embedded Attributes","date":"2024-12-12","arxiv_id":"2412.09442","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 2 unverified","sample_list":"/paper/atprompt-textual-prompt-learning-with#ran","syntology_url":"https://syntology.ai/paper/2412.09442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09442"}},"official":null}},{"url":"/paper/mopi-hfrs-a-multi-objective-personalized","slug":"mopi-hfrs-a-multi-objective-personalized","title":"MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation","date":"2024-12-12","arxiv_id":"2412.08847","repositories_listed":1,"syntology":null},{"url":"/paper/regulation-of-language-models-with","slug":"regulation-of-language-models-with","title":"Regulation of Language Models With Interpretability Will Likely Result In A Performance Trade-Off","date":"2024-12-12","arxiv_id":"2412.12169","repositories_listed":1,"syntology":null},{"url":"/paper/sprec-leveraging-self-play-to-debias","slug":"sprec-leveraging-self-play-to-debias","title":"SPRec: Leveraging Self-Play to Debias Preference Alignment for Large Language Model-based Recommendations","date":"2024-12-12","arxiv_id":"2412.09243","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sprec-leveraging-self-play-to-debias#ran","syntology_url":"https://syntology.ai/paper/2412.09243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09243"}},"official":{"repos":["regionch/sprec"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-multimodal-large-language-model","slug":"towards-a-multimodal-large-language-model","title":"Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine","date":"2024-12-12","arxiv_id":"2412.09278","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-a-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2412.09278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09278"}},"official":{"repos":["shawnhuang497/medplib"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/concept-bottleneck-large-language-models","slug":"concept-bottleneck-large-language-models","title":"Concept Bottleneck Large Language Models","date":"2024-12-11","arxiv_id":"2412.07992","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/concept-bottleneck-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2412.07992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07992"}},"official":{"repos":["trustworthy-ml-lab/cb-llms"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/nyayaanumana-inlegalllama-the-largest-indian","slug":"nyayaanumana-inlegalllama-the-largest-indian","title":"NyayaAnumana & INLegalLlama: The Largest Indian Legal Judgment Prediction Dataset and Specialized Language Model for Enhanced Decision Analysis","date":"2024-12-11","arxiv_id":"2412.08385","repositories_listed":1,"syntology":null},{"url":"/paper/pyod-2-a-python-library-for-outlier-detection","slug":"pyod-2-a-python-library-for-outlier-detection","title":"PyOD 2: A Python Library for Outlier Detection with LLM-powered Model Selection","date":"2024-12-11","arxiv_id":"2412.12154","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/pyod-2-a-python-library-for-outlier-detection#ran","syntology_url":"https://syntology.ai/paper/2412.12154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12154"}},"official":{"repos":["yzhao062/pyod"],"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/bayesian-optimization-of-antibodies-informed","slug":"bayesian-optimization-of-antibodies-informed","title":"Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences","date":"2024-12-10","arxiv_id":"2412.07763","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bayesian-optimization-of-antibodies-informed#ran","syntology_url":"https://syntology.ai/paper/2412.07763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07763"}},"official":{"repos":["alannawzadamin/clonebo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/coprus-consistency-preserving-utterance","slug":"coprus-consistency-preserving-utterance","title":"CoPrUS: Consistency Preserving Utterance Synthesis towards more realistic benchmark dialogues","date":"2024-12-10","arxiv_id":"2412.07515","repositories_listed":1,"syntology":null},{"url":"/paper/granite-guardian","slug":"granite-guardian","title":"Granite Guardian","date":"2024-12-10","arxiv_id":"2412.07724","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/granite-guardian#ran","syntology_url":"https://syntology.ai/paper/2412.07724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07724"}},"official":{"repos":["ibm-granite/granite-guardian"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/intellectseeker-a-personalized-literature","slug":"intellectseeker-a-personalized-literature","title":"IntellectSeeker: A Personalized Literature Management System with the Probabilistic Model and Large Language Model","date":"2024-12-10","arxiv_id":"2412.07213","repositories_listed":1,"syntology":null},{"url":"/paper/llava-spacesgg-visual-instruct-tuning-for","slug":"llava-spacesgg-visual-instruct-tuning-for","title":"LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations","date":"2024-12-09","arxiv_id":"2412.06322","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-generative-ai-to-enhance-automated","slug":"leveraging-generative-ai-to-enhance-automated","title":"Leveraging Generative AI to Enhance Automated Vulnerability Scoring","date":"2024-12-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/video2reward-generating-reward-function-from","slug":"video2reward-generating-reward-function-from","title":"Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning","date":"2024-12-07","arxiv_id":"2412.05515","repositories_listed":1,"syntology":null},{"url":"/paper/expanding-performance-boundaries-of-open","slug":"expanding-performance-boundaries-of-open","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","date":"2024-12-06","arxiv_id":"2412.05271","repositories_listed":1,"syntology":{"n":9,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":8,"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) · 8 unverified","sample_list":"/paper/expanding-performance-boundaries-of-open#ran","syntology_url":"https://syntology.ai/paper/2412.05271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05271"}},"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/linvt-empower-your-image-level-large-language","slug":"linvt-empower-your-image-level-large-language","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","date":"2024-12-06","arxiv_id":"2412.05185","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":6,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/linvt-empower-your-image-level-large-language#ran","syntology_url":"https://syntology.ai/paper/2412.05185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05185"}},"official":{"repos":["gls0425/linvt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/multi-armed-bandit-approach-for-optimizing","slug":"multi-armed-bandit-approach-for-optimizing","title":"Multi-Armed Bandit Approach for Optimizing Training on Synthetic Data","date":"2024-12-06","arxiv_id":"2412.05466","repositories_listed":1,"syntology":null},{"url":"/paper/liquid-language-models-are-scalable-multi","slug":"liquid-language-models-are-scalable-multi","title":"Liquid: Language Models are Scalable Multi-modal Generators","date":"2024-12-05","arxiv_id":"2412.04332","repositories_listed":1,"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":1,"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/liquid-language-models-are-scalable-multi#ran","syntology_url":"https://syntology.ai/paper/2412.04332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04332"}},"official":{"repos":["foundationvision/liquid"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/misr-measuring-instrumental-self-reasoning-in","slug":"misr-measuring-instrumental-self-reasoning-in","title":"MISR: Measuring Instrumental Self-Reasoning in Frontier Models","date":"2024-12-05","arxiv_id":"2412.03904","repositories_listed":1,"syntology":null},{"url":"/paper/synfintabs-a-dataset-of-synthetic-financial","slug":"synfintabs-a-dataset-of-synthetic-financial","title":"SynFinTabs: A Dataset of Synthetic Financial Tables for Information and Table Extraction","date":"2024-12-05","arxiv_id":"2412.04262","repositories_listed":1,"syntology":null},{"url":"/paper/towards-generalizable-autonomous-penetration","slug":"towards-generalizable-autonomous-penetration","title":"Mind the Gap: Towards Generalizable Autonomous Penetration Testing via Domain Randomization and Meta-Reinforcement Learning","date":"2024-12-05","arxiv_id":"2412.04078","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-behavior-simulation-with-role","slug":"fine-grained-behavior-simulation-with-role","title":"Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media","date":"2024-12-04","arxiv_id":"2412.03148","repositories_listed":1,"syntology":null},{"url":"/paper/from-individual-to-society-a-survey-on-social","slug":"from-individual-to-society-a-survey-on-social","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","date":"2024-12-04","arxiv_id":"2412.03563","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-inference-time-search-with-vision","slug":"scaling-inference-time-search-with-vision","title":"Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension","date":"2024-12-04","arxiv_id":"2412.03704","repositories_listed":1,"syntology":null},{"url":"/paper/data-centric-and-heterogeneity-adaptive","slug":"data-centric-and-heterogeneity-adaptive","title":"FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism","date":"2024-12-02","arxiv_id":"2412.01523","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/data-centric-and-heterogeneity-adaptive#ran","syntology_url":"https://syntology.ai/paper/2412.01523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01523"}},"official":null}},{"url":"/paper/hacksynth-llm-agent-and-evaluation-framework","slug":"hacksynth-llm-agent-and-evaluation-framework","title":"HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing","date":"2024-12-02","arxiv_id":"2412.01778","repositories_listed":1,"syntology":null},{"url":"/paper/rilq-rank-insensitive-lora-based-quantization","slug":"rilq-rank-insensitive-lora-based-quantization","title":"RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy","date":"2024-12-02","arxiv_id":"2412.01129","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/rilq-rank-insensitive-lora-based-quantization#ran","syntology_url":"https://syntology.ai/paper/2412.01129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01129"}},"official":{"repos":["aiha-lab/rilq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/free-and-customizable-code-documentation-with","slug":"free-and-customizable-code-documentation-with","title":"Free and Customizable Code Documentation with LLMs: A Fine-Tuning Approach","date":"2024-12-01","arxiv_id":"2412.00726","repositories_listed":1,"syntology":null},{"url":"/paper/covidllm-a-robust-large-language-model-with","slug":"covidllm-a-robust-large-language-model-with","title":"CovidLLM: A Robust Large Language Model with Missing Value Adaptation and Multi-Objective Learning Strategy for Predicting Disease Severity and Clinical Outcomes in COVID-19 Patients","date":"2024-11-28","arxiv_id":"2412.03593","repositories_listed":1,"syntology":null},{"url":"/paper/fastswitch-optimizing-context-switching","slug":"fastswitch-optimizing-context-switching","title":"FastSwitch: Optimizing Context Switching Efficiency in Fairness-aware Large Language Model Serving","date":"2024-11-27","arxiv_id":"2411.18424","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-brained-gui-agents-a","slug":"large-language-model-brained-gui-agents-a","title":"Large Language Model-Brained GUI Agents: A Survey","date":"2024-11-27","arxiv_id":"2411.18279","repositories_listed":1,"syntology":null},{"url":"/paper/apt-architectural-planning-and-text-to","slug":"apt-architectural-planning-and-text-to","title":"APT: Architectural Planning and Text-to-Blueprint Construction Using Large Language Models for Open-World Agents","date":"2024-11-26","arxiv_id":"2411.17255","repositories_listed":1,"syntology":null},{"url":"/paper/hyperseg-towards-universal-visual","slug":"hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}},"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/motionllama-a-unified-framework-for-motion","slug":"motionllama-a-unified-framework-for-motion","title":"MotionLLaMA: A Unified Framework for Motion Synthesis and Comprehension","date":"2024-11-26","arxiv_id":"2411.17335","repositories_listed":1,"syntology":null},{"url":"/paper/openad-open-world-autonomous-driving","slug":"openad-open-world-autonomous-driving","title":"OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection","date":"2024-11-26","arxiv_id":"2411.17761","repositories_listed":1,"syntology":null},{"url":"/paper/ted-viton-transformer-empowered-diffusion","slug":"ted-viton-transformer-empowered-diffusion","title":"TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On","date":"2024-11-26","arxiv_id":"2411.17017","repositories_listed":1,"syntology":null},{"url":"/paper/bayling-2-a-multilingual-large-language-model","slug":"bayling-2-a-multilingual-large-language-model","title":"BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment","date":"2024-11-25","arxiv_id":"2411.16300","repositories_listed":1,"syntology":null},{"url":"/paper/can-a-large-language-model-learn-matrix","slug":"can-a-large-language-model-learn-matrix","title":"Can a Large Language Model Learn Matrix Functions In Context?","date":"2024-11-24","arxiv_id":"2411.15675","repositories_listed":1,"syntology":null},{"url":"/paper/generative-context-distillation","slug":"generative-context-distillation","title":"Generative Prompt Internalization","date":"2024-11-24","arxiv_id":"2411.15927","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/generative-context-distillation#ran","syntology_url":"https://syntology.ai/paper/2411.15927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15927"}},"official":{"repos":["kaistai/generative-context-distillation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/all-that-glitters-approaches-to-evaluations","slug":"all-that-glitters-approaches-to-evaluations","title":"\"All that Glitters\": Approaches to Evaluations with Unreliable Model and Human Annotations","date":"2024-11-23","arxiv_id":"2411.15634","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-with-region-guided","slug":"large-language-model-with-region-guided","title":"Large Language Model with Region-guided Referring and Grounding for CT Report Generation","date":"2024-11-23","arxiv_id":"2411.15539","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-sequential-sentence","slug":"multi-label-sequential-sentence","title":"Multi-label Sequential Sentence Classification via Large Language Model","date":"2024-11-23","arxiv_id":"2411.15623","repositories_listed":1,"syntology":null},{"url":"/paper/scribeagent-towards-specialized-web-agents","slug":"scribeagent-towards-specialized-web-agents","title":"ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data","date":"2024-11-22","arxiv_id":"2411.15004","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/scribeagent-towards-specialized-web-agents#ran","syntology_url":"https://syntology.ai/paper/2411.15004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15004"}},"official":{"repos":["colonylabs/ScribeAgent"],"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/drpruning-efficient-large-language-model","slug":"drpruning-efficient-large-language-model","title":"DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization","date":"2024-11-21","arxiv_id":"2411.14055","repositories_listed":1,"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":1,"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/drpruning-efficient-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2411.14055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14055"}},"official":{"repos":["hexuandeng/drpruning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/piors-personalized-intelligent-outpatient","slug":"piors-personalized-intelligent-outpatient","title":"PIORS: Personalized Intelligent Outpatient Reception based on Large Language Model with Multi-Agents Medical Scenario Simulation","date":"2024-11-21","arxiv_id":"2411.13902","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/piors-personalized-intelligent-outpatient#ran","syntology_url":"https://syntology.ai/paper/2411.13902","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13902"}},"official":{"repos":["fudandisc/piors"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/planning-driven-programming-a-large-language","slug":"planning-driven-programming-a-large-language","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","date":"2024-11-21","arxiv_id":"2411.14503","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/planning-driven-programming-a-large-language#ran","syntology_url":"https://syntology.ai/paper/2411.14503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14503"}},"official":{"repos":["you68681/lpw"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/semikong-curating-training-and-evaluating-a","slug":"semikong-curating-training-and-evaluating-a","title":"SemiKong: Curating, Training, and Evaluating A Semiconductor Industry-Specific Large Language Model","date":"2024-11-21","arxiv_id":"2411.13802","repositories_listed":1,"syntology":null},{"url":"/paper/reflections-from-the-2024-large-language","slug":"reflections-from-the-2024-large-language","title":"Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry","date":"2024-11-20","arxiv_id":"2411.15221","repositories_listed":1,"syntology":null},{"url":"/paper/robust-planning-with-compound-llm","slug":"robust-planning-with-compound-llm","title":"Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach","date":"2024-11-20","arxiv_id":"2411.14484","repositories_listed":1,"syntology":null},{"url":"/paper/suspected-undeclared-use-of-artificial","slug":"suspected-undeclared-use-of-artificial","title":"Suspected Undeclared Use of Artificial Intelligence in the Academic Literature: An Analysis of the Academ-AI Dataset","date":"2024-11-20","arxiv_id":"2411.15218","repositories_listed":1,"syntology":null},{"url":"/paper/probing-the-capacity-of-language-model-agents","slug":"probing-the-capacity-of-language-model-agents","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","date":"2024-11-19","arxiv_id":"2411.12828","repositories_listed":1,"syntology":null},{"url":"/paper/ranking-unraveled-recipes-for-llm-rankings-in","slug":"ranking-unraveled-recipes-for-llm-rankings-in","title":"Ranking Unraveled: Recipes for LLM Rankings in Head-to-Head AI Combat","date":"2024-11-19","arxiv_id":"2411.14483","repositories_listed":1,"syntology":null},{"url":"/paper/does-unlearning-truly-unlearn-a-black-box","slug":"does-unlearning-truly-unlearn-a-black-box","title":"Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods","date":"2024-11-18","arxiv_id":"2411.12103","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/does-unlearning-truly-unlearn-a-black-box#ran","syntology_url":"https://syntology.ai/paper/2411.12103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12103"}},"official":{"repos":["jaidoshi/knowledge-erasure"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-mllm-embeddings-and-attribute","slug":"leveraging-mllm-embeddings-and-attribute","title":"Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning","date":"2024-11-18","arxiv_id":"2411.12584","repositories_listed":1,"syntology":null},{"url":"/paper/oasis-open-agents-social-interaction","slug":"oasis-open-agents-social-interaction","title":"OASIS: Open Agent Social Interaction Simulations with One Million Agents","date":"2024-11-18","arxiv_id":"2411.11581","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/oasis-open-agents-social-interaction#ran","syntology_url":"https://syntology.ai/paper/2411.11581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11581"}},"official":{"repos":["camel-ai/oasis"],"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/topology-aware-preemptive-scheduling-for-co","slug":"topology-aware-preemptive-scheduling-for-co","title":"Topology-aware Preemptive Scheduling for Co-located LLM Workloads","date":"2024-11-18","arxiv_id":"2411.11560","repositories_listed":1,"syntology":null},{"url":"/paper/tsinr-capturing-temporal-continuity-via","slug":"tsinr-capturing-temporal-continuity-via","title":"TSINR: Capturing Temporal Continuity via Implicit Neural Representations for Time Series Anomaly Detection","date":"2024-11-18","arxiv_id":"2411.11641","repositories_listed":1,"syntology":null},{"url":"/paper/biancang-a-traditional-chinese-medicine-large","slug":"biancang-a-traditional-chinese-medicine-large","title":"BianCang: A Traditional Chinese Medicine Large Language Model","date":"2024-11-17","arxiv_id":"2411.11027","repositories_listed":1,"syntology":null},{"url":"/paper/multi-stage-vision-token-dropping-towards","slug":"multi-stage-vision-token-dropping-towards","title":"Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model","date":"2024-11-16","arxiv_id":"2411.10803","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-stage-vision-token-dropping-towards#ran","syntology_url":"https://syntology.ai/paper/2411.10803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10803"}},"official":{"repos":["liuting20/mustdrop"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/structured-dialogue-system-for-mental-health","slug":"structured-dialogue-system-for-mental-health","title":"Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines","date":"2024-11-16","arxiv_id":"2411.10681","repositories_listed":1,"syntology":null},{"url":"/paper/xmodel-1-5-an-1b-scale-multilingual-llm","slug":"xmodel-1-5-an-1b-scale-multilingual-llm","title":"Xmodel-1.5: An 1B-scale Multilingual LLM","date":"2024-11-15","arxiv_id":"2411.10083","repositories_listed":1,"syntology":null},{"url":"/paper/lhrs-bot-nova-improved-multimodal-large","slug":"lhrs-bot-nova-improved-multimodal-large","title":"LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation","date":"2024-11-14","arxiv_id":"2411.09301","repositories_listed":1,"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":5,"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/lhrs-bot-nova-improved-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2411.09301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09301"}},"official":{"repos":["NJU-LHRS/LHRS-Bot"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/magicquill-an-intelligent-interactive-image","slug":"magicquill-an-intelligent-interactive-image","title":"MagicQuill: An Intelligent Interactive Image Editing System","date":"2024-11-14","arxiv_id":"2411.09703","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":12,"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) · 0 unverified","sample_list":"/paper/magicquill-an-intelligent-interactive-image#ran","syntology_url":"https://syntology.ai/paper/2411.09703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09703"}},"official":{"repos":["ant-research/MagicQuill"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reducing-reasoning-costs-the-path-of","slug":"reducing-reasoning-costs-the-path-of","title":"Reducing Reasoning Costs: The Path of Optimization for Chain of Thought via Sparse Attention Mechanism","date":"2024-11-14","arxiv_id":"2411.09111","repositories_listed":1,"syntology":null},{"url":"/paper/squeezed-attention-accelerating-long-context","slug":"squeezed-attention-accelerating-long-context","title":"Squeezed Attention: Accelerating Long Context Length LLM Inference","date":"2024-11-14","arxiv_id":"2411.09688","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":15,"phrase":"12 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/squeezed-attention-accelerating-long-context#ran","syntology_url":"https://syntology.ai/paper/2411.09688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09688"}},"official":{"repos":["SqueezeAILab/SqueezedAttention"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/janusflow-harmonizing-autoregression-and","slug":"janusflow-harmonizing-autoregression-and","title":"JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation","date":"2024-11-12","arxiv_id":"2411.07975","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-as-causal-effect-generators","slug":"language-models-as-causal-effect-generators","title":"Language Models as Causal Effect Generators","date":"2024-11-12","arxiv_id":"2411.08019","repositories_listed":1,"syntology":null},{"url":"/paper/building-a-taiwanese-mandarin-spoken-language","slug":"building-a-taiwanese-mandarin-spoken-language","title":"Building a Taiwanese Mandarin Spoken Language Model: A First Attempt","date":"2024-11-11","arxiv_id":"2411.07111","repositories_listed":1,"syntology":null},{"url":"/paper/music-discovery-dialogue-generation-using","slug":"music-discovery-dialogue-generation-using","title":"Music Discovery Dialogue Generation Using Human Intent Analysis and Large Language Models","date":"2024-11-11","arxiv_id":"2411.07439","repositories_listed":1,"syntology":null},{"url":"/paper/storyteller-improving-long-video-description","slug":"storyteller-improving-long-video-description","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","date":"2024-11-11","arxiv_id":"2411.07076","repositories_listed":1,"syntology":null},{"url":"/paper/the-super-weight-in-large-language-models","slug":"the-super-weight-in-large-language-models","title":"The Super Weight in Large Language Models","date":"2024-11-11","arxiv_id":"2411.07191","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"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) · 4 unverified","sample_list":"/paper/the-super-weight-in-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2411.07191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07191"}},"official":{"repos":["mengxiayu/llmsuperweight"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/ctc-assisted-llm-based-contextual-asr","slug":"ctc-assisted-llm-based-contextual-asr","title":"CTC-Assisted LLM-Based Contextual ASR","date":"2024-11-10","arxiv_id":"2411.06437","repositories_listed":1,"syntology":null},{"url":"/paper/a-taxonomy-of-agentops-for-enabling","slug":"a-taxonomy-of-agentops-for-enabling","title":"AgentOps: Enabling Observability of LLM Agents","date":"2024-11-08","arxiv_id":"2411.05285","repositories_listed":1,"syntology":null},{"url":"/paper/a-two-step-concept-based-approach-for","slug":"a-two-step-concept-based-approach-for","title":"A Two-Step Concept-Based Approach for Enhanced Interpretability and Trust in Skin Lesion Diagnosis","date":"2024-11-08","arxiv_id":"2411.05609","repositories_listed":1,"syntology":null},{"url":"/paper/eurekha-enhancing-user-representation-for-key","slug":"eurekha-enhancing-user-representation-for-key","title":"EUREKHA: Enhancing User Representation for Key Hackers Identification in Underground Forums","date":"2024-11-08","arxiv_id":"2411.05479","repositories_listed":1,"syntology":null},{"url":"/paper/intellbot-retrieval-augmented-llm-chatbot-for","slug":"intellbot-retrieval-augmented-llm-chatbot-for","title":"IntellBot: Retrieval Augmented LLM Chatbot for Cyber Threat Knowledge Delivery","date":"2024-11-08","arxiv_id":"2411.05442","repositories_listed":1,"syntology":null},{"url":"/paper/learning-the-rules-of-peptide-self-assembly","slug":"learning-the-rules-of-peptide-self-assembly","title":"Learning the rules of peptide self-assembly through data mining with large language models","date":"2024-11-08","arxiv_id":"2411.05421","repositories_listed":1,"syntology":null},{"url":"/paper/llm-pysc2-starcraft-ii-learning-environment","slug":"llm-pysc2-starcraft-ii-learning-environment","title":"LLM-PySC2: Starcraft II learning environment for Large Language Models","date":"2024-11-08","arxiv_id":"2411.05348","repositories_listed":1,"syntology":null},{"url":"/paper/autoproteinengine-a-large-language-model","slug":"autoproteinengine-a-large-language-model","title":"AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering","date":"2024-11-07","arxiv_id":"2411.04440","repositories_listed":1,"syntology":null},{"url":"/paper/capo-cooperative-plan-optimization-for","slug":"capo-cooperative-plan-optimization-for","title":"CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation","date":"2024-11-07","arxiv_id":"2411.04679","repositories_listed":1,"syntology":null},{"url":"/paper/gptkb-building-very-large-knowledge-bases","slug":"gptkb-building-very-large-knowledge-bases","title":"Enabling LLM Knowledge Analysis via Extensive Materialization","date":"2024-11-07","arxiv_id":"2411.04920","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-bradley-terry-models-in-preference","slug":"rethinking-bradley-terry-models-in-preference","title":"Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives","date":"2024-11-07","arxiv_id":"2411.04991","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/rethinking-bradley-terry-models-in-preference#ran","syntology_url":"https://syntology.ai/paper/2411.04991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04991"}},"official":{"repos":["holarissun/rewardmodelingbeyondbradleyterry"],"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/suffixdecoding-a-model-free-approach-to","slug":"suffixdecoding-a-model-free-approach-to","title":"SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications","date":"2024-11-07","arxiv_id":"2411.04975","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/suffixdecoding-a-model-free-approach-to#ran","syntology_url":"https://syntology.ai/paper/2411.04975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04975"}},"official":{"repos":["snowflakedb/arcticinference"],"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/thanos-enhancing-conversational-agents-with","slug":"thanos-enhancing-conversational-agents-with","title":"Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model","date":"2024-11-07","arxiv_id":"2411.04496","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-large-language-models-in-code","slug":"leveraging-large-language-models-in-code","title":"Leveraging Large Language Models in Code Question Answering: Baselines and Issues","date":"2024-11-05","arxiv_id":"2411.03012","repositories_listed":1,"syntology":null},{"url":"/paper/v-dpo-mitigating-hallucination-in-large","slug":"v-dpo-mitigating-hallucination-in-large","title":"V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization","date":"2024-11-05","arxiv_id":"2411.02712","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/v-dpo-mitigating-hallucination-in-large#ran","syntology_url":"https://syntology.ai/paper/2411.02712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02712"}},"official":{"repos":["yuxixie/v-dpo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ragviz-diagnose-and-visualize-retrieval","slug":"ragviz-diagnose-and-visualize-retrieval","title":"RAGViz: Diagnose and Visualize Retrieval-Augmented Generation","date":"2024-11-04","arxiv_id":"2411.01751","repositories_listed":1,"syntology":null},{"url":"/paper/zebra-llama-a-context-aware-large-language","slug":"zebra-llama-a-context-aware-large-language","title":"Zebra-Llama: A Context-Aware Large Language Model for Democratizing Rare Disease Knowledge","date":"2024-11-04","arxiv_id":"2411.02657","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-large-language-models-for-code-1","slug":"leveraging-large-language-models-for-code-1","title":"Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis","date":"2024-11-01","arxiv_id":"2411.00691","repositories_listed":1,"syntology":null},{"url":"/paper/multi-expert-prompting-improves-reliability","slug":"multi-expert-prompting-improves-reliability","title":"Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models","date":"2024-11-01","arxiv_id":"2411.00492","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/multi-expert-prompting-improves-reliability#ran","syntology_url":"https://syntology.ai/paper/2411.00492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00492"}},"official":{"repos":["dxlong2000/multi-expert-prompting"],"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/echonarrator-generating-natural-text","slug":"echonarrator-generating-natural-text","title":"EchoNarrator: Generating natural text explanations for ejection fraction predictions","date":"2024-10-31","arxiv_id":"2410.23744","repositories_listed":1,"syntology":null},{"url":"/paper/ez-hoi-vlm-adaptation-via-guided-prompt","slug":"ez-hoi-vlm-adaptation-via-guided-prompt","title":"EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection","date":"2024-10-31","arxiv_id":"2410.23904","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ez-hoi-vlm-adaptation-via-guided-prompt#ran","syntology_url":"https://syntology.ai/paper/2410.23904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23904"}},"official":{"repos":["chelsielei/ez-hoi"],"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/instruction-tuning-llama-3-8b-excels-in-city","slug":"instruction-tuning-llama-3-8b-excels-in-city","title":"Instruction-Tuning Llama-3-8B Excels in City-Scale Mobility Prediction","date":"2024-10-31","arxiv_id":"2410.23692","repositories_listed":1,"syntology":null},{"url":"/paper/llamo-large-language-model-based-molecular","slug":"llamo-large-language-model-based-molecular","title":"LLaMo: Large Language Model-based Molecular Graph Assistant","date":"2024-10-31","arxiv_id":"2411.00871","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llamo-large-language-model-based-molecular#ran","syntology_url":"https://syntology.ai/paper/2411.00871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00871"}},"official":{"repos":["mlvlab/llamo"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-ontology-in-dialogue-state-tracking","slug":"beyond-ontology-in-dialogue-state-tracking","title":"Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot","date":"2024-10-30","arxiv_id":"2410.22767","repositories_listed":1,"syntology":null}],"record_sha256":"6e7d79ec0c0492e2dd6cdf190492fc33fd22853f9691e669b5e4527632404023","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}