{"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/12","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":12,"pages_in_order":61,"rows_per_page":100,"rows":[1101,1200],"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/11","next":"/task/large-language-model/papers/13","papers":[{"url":"/paper/a-comparison-of-large-language-model-and","slug":"a-comparison-of-large-language-model-and","title":"A Comparison of Large Language Model and Human Performance on Random Number Generation Tasks","date":"2024-08-19","arxiv_id":"2408.09656","repositories_listed":1,"syntology":null},{"url":"/paper/attribution-analysis-meets-model-editing","slug":"attribution-analysis-meets-model-editing","title":"Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit","date":"2024-08-19","arxiv_id":"2408.09916","repositories_listed":1,"syntology":null},{"url":"/paper/automl-guided-fusion-of-entity-and-llm-based","slug":"automl-guided-fusion-of-entity-and-llm-based","title":"AutoML-guided Fusion of Entity and LLM-based Representations for Document Classification","date":"2024-08-19","arxiv_id":"2408.09794","repositories_listed":1,"syntology":null},{"url":"/paper/cmoraleval-a-moral-evaluation-benchmark-for","slug":"cmoraleval-a-moral-evaluation-benchmark-for","title":"CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models","date":"2024-08-19","arxiv_id":"2408.09819","repositories_listed":1,"syntology":null},{"url":"/paper/ffaa-multimodal-large-language-model-based","slug":"ffaa-multimodal-large-language-model-based","title":"FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant","date":"2024-08-19","arxiv_id":"2408.10072","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/ffaa-multimodal-large-language-model-based#ran","syntology_url":"https://syntology.ai/paper/2408.10072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10072"}},"official":{"repos":["thu-huangzc/FFAA"],"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/harnessing-multimodal-large-language-models","slug":"harnessing-multimodal-large-language-models","title":"Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation","date":"2024-08-19","arxiv_id":"2408.09698","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/harnessing-multimodal-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2408.09698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09698"}},"official":{"repos":["yuyangye/mllm-msr"],"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/idea-enhancing-the-rule-learning-ability-of","slug":"idea-enhancing-the-rule-learning-ability-of","title":"IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction","date":"2024-08-19","arxiv_id":"2408.10455","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/idea-enhancing-the-rule-learning-ability-of#ran","syntology_url":"https://syntology.ai/paper/2408.10455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10455"}},"official":{"repos":["kaiyuhe998/rulearn_idea"],"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/r2gencsr-retrieving-context-samples-for-large","slug":"r2gencsr-retrieving-context-samples-for-large","title":"R2GenCSR: Retrieving Context Samples for Large Language Model based X-ray Medical Report Generation","date":"2024-08-19","arxiv_id":"2408.09743","repositories_listed":1,"syntology":null},{"url":"/paper/hiagent-hierarchical-working-memory","slug":"hiagent-hierarchical-working-memory","title":"HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model","date":"2024-08-18","arxiv_id":"2408.09559","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hiagent-hierarchical-working-memory#ran","syntology_url":"https://syntology.ai/paper/2408.09559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09559"}},"official":{"repos":["hiagent2024/hiagent"],"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/generating-data-with-text-to-speech-and-large","slug":"generating-data-with-text-to-speech-and-large","title":"Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition","date":"2024-08-17","arxiv_id":"2408.09215","repositories_listed":1,"syntology":null},{"url":"/paper/an-end-to-end-model-for-photo-sharing-multi","slug":"an-end-to-end-model-for-photo-sharing-multi","title":"An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation","date":"2024-08-16","arxiv_id":"2408.08650","repositories_listed":1,"syntology":null},{"url":"/paper/roargraph-a-projected-bipartite-graph-for","slug":"roargraph-a-projected-bipartite-graph-for","title":"RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search","date":"2024-08-16","arxiv_id":"2408.08933","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-validity-of-word-level","slug":"evaluating-the-validity-of-word-level","title":"Evaluating the Validity of Word-level Adversarial Attacks with Large Language Models","date":"2024-08-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/text2bim-generating-building-models-using-a","slug":"text2bim-generating-building-models-using-a","title":"Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework","date":"2024-08-15","arxiv_id":"2408.08054","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":1,"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/text2bim-generating-building-models-using-a#ran","syntology_url":"https://syntology.ai/paper/2408.08054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08054"}},"official":{"repos":["dcy0577/Text2BIM"],"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/medtsllm-leveraging-llms-for-multimodal","slug":"medtsllm-leveraging-llms-for-multimodal","title":"MedTsLLM: Leveraging LLMs for Multimodal Medical Time Series Analysis","date":"2024-08-14","arxiv_id":"2408.07773","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-and-understanding-bridging-vision-with","slug":"seeing-and-understanding-bridging-vision-with","title":"ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area","date":"2024-08-14","arxiv_id":"2408.07246","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seeing-and-understanding-bridging-vision-with#ran","syntology_url":"https://syntology.ai/paper/2408.07246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07246"}},"official":{"repos":["AI4Chem/ChemVlm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/causal-agent-based-on-large-language-model","slug":"causal-agent-based-on-large-language-model","title":"Causal Agent based on Large Language Model","date":"2024-08-13","arxiv_id":"2408.06849","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/causal-agent-based-on-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2408.06849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06849"}},"official":{"repos":["kairong-han/causal_agent"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-cultural-adaptability-of-a-large","slug":"evaluating-cultural-adaptability-of-a-large","title":"Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas","date":"2024-08-13","arxiv_id":"2408.06929","repositories_listed":1,"syntology":null},{"url":"/paper/neural-embedding-of-beliefs-reveals-the-role","slug":"neural-embedding-of-beliefs-reveals-the-role","title":"A semantic embedding space based on large language models for modelling human beliefs","date":"2024-08-13","arxiv_id":"2408.07237","repositories_listed":1,"syntology":null},{"url":"/paper/fuxitranyu-a-multilingual-large-language","slug":"fuxitranyu-a-multilingual-large-language","title":"FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data","date":"2024-08-12","arxiv_id":"2408.06273","repositories_listed":1,"syntology":null},{"url":"/paper/on-effects-of-steering-latent-representation","slug":"on-effects-of-steering-latent-representation","title":"On Effects of Steering Latent Representation for Large Language Model Unlearning","date":"2024-08-12","arxiv_id":"2408.06223","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-effects-of-steering-latent-representation#ran","syntology_url":"https://syntology.ai/paper/2408.06223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06223"}},"official":{"repos":["RebelsNLU-jaist/llm-unlearning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/prompto-an-open-source-library-for","slug":"prompto-an-open-source-library-for","title":"Prompto: An open source library for asynchronous querying of LLM endpoints","date":"2024-08-12","arxiv_id":"2408.11847","repositories_listed":1,"syntology":null},{"url":"/paper/xcompress-llm-assisted-python-based-text","slug":"xcompress-llm-assisted-python-based-text","title":"XCompress: LLM assisted Python-based text compression toolkit","date":"2024-08-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/llmservingsim-a-hw-sw-co-simulation","slug":"llmservingsim-a-hw-sw-co-simulation","title":"LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale","date":"2024-08-10","arxiv_id":"2408.05499","repositories_listed":1,"syntology":null},{"url":"/paper/vic-virtual-compiler-is-all-you-need-for","slug":"vic-virtual-compiler-is-all-you-need-for","title":"ViC: Virtual Compiler Is All You Need For Assembly Code Search","date":"2024-08-10","arxiv_id":"2408.06385","repositories_listed":1,"syntology":null},{"url":"/paper/llava-vsd-large-language-and-vision-assistant","slug":"llava-vsd-large-language-and-vision-assistant","title":"LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description","date":"2024-08-09","arxiv_id":"2408.04957","repositories_listed":1,"syntology":null},{"url":"/paper/mplug-owl3-towards-long-image-sequence","slug":"mplug-owl3-towards-long-image-sequence","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","date":"2024-08-09","arxiv_id":"2408.04840","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-episode-detection-for-large","slug":"unsupervised-episode-detection-for-large","title":"Unsupervised Episode Detection for Large-Scale News Events","date":"2024-08-09","arxiv_id":"2408.04873","repositories_listed":1,"syntology":null},{"url":"/paper/vita-towards-open-source-interactive-omni","slug":"vita-towards-open-source-interactive-omni","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","date":"2024-08-09","arxiv_id":"2408.05211","repositories_listed":1,"syntology":null},{"url":"/paper/conversational-ai-powered-by-large-language","slug":"conversational-ai-powered-by-large-language","title":"Conversational AI Powered by Large Language Models Amplifies False Memories in Witness Interviews","date":"2024-08-08","arxiv_id":"2408.04681","repositories_listed":1,"syntology":null},{"url":"/paper/medical-graph-rag-towards-safe-medical-large","slug":"medical-graph-rag-towards-safe-medical-large","title":"Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation","date":"2024-08-08","arxiv_id":"2408.04187","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/medical-graph-rag-towards-safe-medical-large#ran","syntology_url":"https://syntology.ai/paper/2408.04187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04187"}},"official":{"repos":["medicinetoken/medical-graph-rag"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/open-domain-implicit-format-control-for-large","slug":"open-domain-implicit-format-control-for-large","title":"Open-domain Implicit Format Control for Large Language Model Generation","date":"2024-08-08","arxiv_id":"2408.04392","repositories_listed":1,"syntology":null},{"url":"/paper/egybert-a-large-language-model-pretrained-on","slug":"egybert-a-large-language-model-pretrained-on","title":"EgyBERT: A Large Language Model Pretrained on Egyptian Dialect Corpora","date":"2024-08-07","arxiv_id":"2408.03524","repositories_listed":1,"syntology":null},{"url":"/paper/openstory-a-large-scale-dataset-and-benchmark","slug":"openstory-a-large-scale-dataset-and-benchmark","title":"Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling","date":"2024-08-07","arxiv_id":"2408.03695","repositories_listed":1,"syntology":null},{"url":"/paper/walledeval-a-comprehensive-safety-evaluation","slug":"walledeval-a-comprehensive-safety-evaluation","title":"WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models","date":"2024-08-07","arxiv_id":"2408.03837","repositories_listed":1,"syntology":null},{"url":"/paper/2408-03094","slug":"2408-03094","title":"500xCompressor: Generalized Prompt Compression for Large Language Models","date":"2024-08-06","arxiv_id":"2408.03094","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-03094#ran","syntology_url":"https://syntology.ai/paper/2408.03094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03094"}},"official":{"repos":["ZongqianLi/500xCompressor"],"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/2408-03127","slug":"2408-03127","title":"Lisbon Computational Linguists at SemEval-2024 Task 2: Using A Mistral 7B Model and Data Augmentation","date":"2024-08-06","arxiv_id":"2408.03127","repositories_listed":1,"syntology":null},{"url":"/paper/2408-03281","slug":"2408-03281","title":"StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation","date":"2024-08-06","arxiv_id":"2408.03281","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":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/2408-03281#ran","syntology_url":"https://syntology.ai/paper/2408.03281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03281"}},"official":{"repos":["c-box/structeval"],"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/citekit-a-modular-toolkit-for-large-language","slug":"citekit-a-modular-toolkit-for-large-language","title":"Citekit: A Modular Toolkit for Large Language Model Citation Generation","date":"2024-08-06","arxiv_id":"2408.04662","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/citekit-a-modular-toolkit-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2408.04662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04662"}},"official":{"repos":["sjj1017/citekit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ullme-a-unified-framework-for-large-language","slug":"ullme-a-unified-framework-for-large-language","title":"ULLME: A Unified Framework for Large Language Model Embeddings with Generation-Augmented Learning","date":"2024-08-06","arxiv_id":"2408.03402","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ullme-a-unified-framework-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2408.03402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03402"}},"official":{"repos":["nlp-uoregon/ullme"],"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/2408-02503","slug":"2408-02503","title":"UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model","date":"2024-08-05","arxiv_id":"2408.02503","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02544","slug":"2408-02544","title":"Caution for the Environment: Multimodal Agents are Susceptible to Environmental Distractions","date":"2024-08-05","arxiv_id":"2408.02544","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-02544#ran","syntology_url":"https://syntology.ai/paper/2408.02544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02544"}},"official":{"repos":["xbmxb/EnvDistraction"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/xmainframe-a-large-language-model-for","slug":"xmainframe-a-large-language-model-for","title":"XMainframe: A Large Language Model for Mainframe Modernization","date":"2024-08-05","arxiv_id":"2408.04660","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00989","slug":"2408-00989","title":"On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents","date":"2024-08-02","arxiv_id":"2408.00989","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/2408-00989#ran","syntology_url":"https://syntology.ai/paper/2408.00989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00989"}},"official":{"repos":["cuhk-arise/mas-resilience"],"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/2408-00357","slug":"2408-00357","title":"DeliLaw: A Chinese Legal Counselling System Based on a Large Language Model","date":"2024-08-01","arxiv_id":"2408.00357","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00523","slug":"2408-00523","title":"Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models","date":"2024-08-01","arxiv_id":"2408.00523","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00764","slug":"2408-00764","title":"AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation","date":"2024-08-01","arxiv_id":"2408.00764","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/2408-00764#ran","syntology_url":"https://syntology.ai/paper/2408.00764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00764"}},"official":{"repos":["lazychih114/AgentGen-Reproduction"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/language-driven-slice-discovery-and-error","slug":"language-driven-slice-discovery-and-error","title":"LADDER: Language Driven Slice Discovery and Error Rectification","date":"2024-07-31","arxiv_id":"2408.07832","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":17,"phrase":"15 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/language-driven-slice-discovery-and-error#ran","syntology_url":"https://syntology.ai/paper/2408.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07832"}},"official":null}},{"url":"/paper/2407-21170","slug":"2407-21170","title":"Decomposed Prompting to Answer Questions on a Course Discussion Board","date":"2024-07-30","arxiv_id":"2407.21170","repositories_listed":1,"syntology":null},{"url":"/paper/cleft-language-image-contrastive-learning","slug":"cleft-language-image-contrastive-learning","title":"CLEFT: Language-Image Contrastive Learning with Efficient Large Language Model and Prompt Fine-Tuning","date":"2024-07-30","arxiv_id":"2407.21011","repositories_listed":1,"syntology":null},{"url":"/paper/optimus-0-3-using-large-language-models-to","slug":"optimus-0-3-using-large-language-models-to","title":"OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale","date":"2024-07-29","arxiv_id":"2407.19633","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":3,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/optimus-0-3-using-large-language-models-to#ran","syntology_url":"https://syntology.ai/paper/2407.19633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19633"}},"official":null}},{"url":"/paper/prometheus-chatbot-knowledge-graph","slug":"prometheus-chatbot-knowledge-graph","title":"Prometheus Chatbot: Knowledge Graph Collaborative Large Language Model for Computer Components Recommendation","date":"2024-07-29","arxiv_id":"2407.19643","repositories_listed":1,"syntology":null},{"url":"/paper/a-role-specific-guided-large-language-model","slug":"a-role-specific-guided-large-language-model","title":"A Role-specific Guided Large Language Model for Ophthalmic Consultation Based on Stylistic Differentiation","date":"2024-07-26","arxiv_id":"2407.18483","repositories_listed":1,"syntology":null},{"url":"/paper/solving-robotics-problems-in-zero-shot-with","slug":"solving-robotics-problems-in-zero-shot-with","title":"Wonderful Team: Zero-Shot Physical Task Planning with Visual LLMs","date":"2024-07-26","arxiv_id":"2407.19094","repositories_listed":1,"syntology":null},{"url":"/paper/cost-effective-instruction-learning-for","slug":"cost-effective-instruction-learning-for","title":"Cost-effective Instruction Learning for Pathology Vision and Language Analysis","date":"2024-07-25","arxiv_id":"2407.17734","repositories_listed":1,"syntology":null},{"url":"/paper/can-language-models-evaluate-human-written","slug":"can-language-models-evaluate-human-written","title":"Can Language Models Evaluate Human Written Text? Case Study on Korean Student Writing for Education","date":"2024-07-24","arxiv_id":"2407.17022","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-leverage-personal-textual-knowledge","slug":"how-to-leverage-personal-textual-knowledge","title":"How to Leverage Personal Textual Knowledge for Personalized Conversational Information Retrieval","date":"2024-07-23","arxiv_id":"2407.16192","repositories_listed":1,"syntology":null},{"url":"/paper/inf-llava-dual-perspective-perception-for","slug":"inf-llava-dual-perspective-perception-for","title":"INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model","date":"2024-07-23","arxiv_id":"2407.16198","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/inf-llava-dual-perspective-perception-for#ran","syntology_url":"https://syntology.ai/paper/2407.16198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16198"}},"official":{"repos":["weihuanglin/inf-llava"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/dstruct2design-data-and-benchmarks-for-data","slug":"dstruct2design-data-and-benchmarks-for-data","title":"DStruct2Design: Data and Benchmarks for Data Structure Driven Generative Floor Plan Design","date":"2024-07-22","arxiv_id":"2407.15723","repositories_listed":1,"syntology":null},{"url":"/paper/llast-improved-end-to-end-speech-translation","slug":"llast-improved-end-to-end-speech-translation","title":"LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models","date":"2024-07-22","arxiv_id":"2407.15415","repositories_listed":1,"syntology":null},{"url":"/paper/odyssey-empowering-agents-with-open-world","slug":"odyssey-empowering-agents-with-open-world","title":"Odyssey: Empowering Minecraft Agents with Open-World Skills","date":"2024-07-22","arxiv_id":"2407.15325","repositories_listed":1,"syntology":null},{"url":"/paper/slowfast-llava-a-strong-training-free","slug":"slowfast-llava-a-strong-training-free","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","date":"2024-07-22","arxiv_id":"2407.15841","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/slowfast-llava-a-strong-training-free#ran","syntology_url":"https://syntology.ai/paper/2407.15841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15841"}},"official":{"repos":["apple/ml-slowfast-llava"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/taskgen-a-task-based-memory-infused-agentic","slug":"taskgen-a-task-based-memory-infused-agentic","title":"TaskGen: A Task-Based, Memory-Infused Agentic Framework using StrictJSON","date":"2024-07-22","arxiv_id":"2407.15734","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-for-verilog-generation","slug":"large-language-model-for-verilog-generation","title":"Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning","date":"2024-07-21","arxiv_id":"2407.18271","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-model-for-verilog-generation#ran","syntology_url":"https://syntology.ai/paper/2407.18271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18271"}},"official":{"repos":["CatIIIIIIII/veriseek"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-classification-of-news-subjects-in","slug":"automatic-classification-of-news-subjects-in","title":"Automatic Classification of News Subjects in Broadcast News: Application to a Gender Bias Representation Analysis","date":"2024-07-19","arxiv_id":"2407.14180","repositories_listed":1,"syntology":null},{"url":"/paper/conditioning-chat-gpt-for-information","slug":"conditioning-chat-gpt-for-information","title":"Unipa-GPT: Large Language Models for university-oriented QA in Italian","date":"2024-07-19","arxiv_id":"2407.14246","repositories_listed":1,"syntology":null},{"url":"/paper/rag-qa-arena-evaluating-domain-robustness-for","slug":"rag-qa-arena-evaluating-domain-robustness-for","title":"RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering","date":"2024-07-19","arxiv_id":"2407.13998","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rag-qa-arena-evaluating-domain-robustness-for#ran","syntology_url":"https://syntology.ai/paper/2407.13998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13998"}},"official":{"repos":["awslabs/rag-qa-arena"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/t2v-compbench-a-comprehensive-benchmark-for","slug":"t2v-compbench-a-comprehensive-benchmark-for","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","date":"2024-07-19","arxiv_id":"2407.14505","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/t2v-compbench-a-comprehensive-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2407.14505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14505"}},"official":{"repos":["KaiyueSun98/T2V-CompBench"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-text-generation-in-the-wild","slug":"visual-text-generation-in-the-wild","title":"Visual Text Generation in the Wild","date":"2024-07-19","arxiv_id":"2407.14138","repositories_listed":1,"syntology":null},{"url":"/paper/earthmarker-a-visual-prompt-learning","slug":"earthmarker-a-visual-prompt-learning","title":"EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing","date":"2024-07-18","arxiv_id":"2407.13596","repositories_listed":1,"syntology":null},{"url":"/paper/villa-video-reasoning-segmentation-with-large","slug":"villa-video-reasoning-segmentation-with-large","title":"ViLLa: Video Reasoning Segmentation with Large Language Model","date":"2024-07-18","arxiv_id":"2407.14500","repositories_listed":1,"syntology":null},{"url":"/paper/spectra-a-comprehensive-study-of-ternary","slug":"spectra-a-comprehensive-study-of-ternary","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","date":"2024-07-17","arxiv_id":"2407.12327","repositories_listed":1,"syntology":null},{"url":"/paper/how-personality-traits-influence-negotiation","slug":"how-personality-traits-influence-negotiation","title":"How Personality Traits Influence Negotiation Outcomes? A Simulation based on Large Language Models","date":"2024-07-16","arxiv_id":"2407.11549","repositories_listed":1,"syntology":null},{"url":"/paper/invagent-a-large-language-model-based-multi","slug":"invagent-a-large-language-model-based-multi","title":"InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains","date":"2024-07-16","arxiv_id":"2407.11384","repositories_listed":1,"syntology":null},{"url":"/paper/urbanworld-an-urban-world-model-for-3d-city","slug":"urbanworld-an-urban-world-model-for-3d-city","title":"UrbanWorld: An Urban World Model for 3D City Generation","date":"2024-07-16","arxiv_id":"2407.11965","repositories_listed":1,"syntology":null},{"url":"/paper/an-actionable-framework-for-assessing-bias","slug":"an-actionable-framework-for-assessing-bias","title":"An Actionable Framework for Assessing Bias and Fairness in Large Language Model Use Cases","date":"2024-07-15","arxiv_id":"2407.10853","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-actionable-framework-for-assessing-bias#ran","syntology_url":"https://syntology.ai/paper/2407.10853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10853"}},"official":{"repos":["cvs-health/langfair"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/can-textual-semantics-mitigate-sounding","slug":"can-textual-semantics-mitigate-sounding","title":"Can Textual Semantics Mitigate Sounding Object Segmentation Preference?","date":"2024-07-15","arxiv_id":"2407.10947","repositories_listed":1,"syntology":null},{"url":"/paper/docbench-a-benchmark-for-evaluating-llm-based","slug":"docbench-a-benchmark-for-evaluating-llm-based","title":"DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems","date":"2024-07-15","arxiv_id":"2407.10701","repositories_listed":1,"syntology":null},{"url":"/paper/grutopia-dream-general-robots-in-a-city-at","slug":"grutopia-dream-general-robots-in-a-city-at","title":"GRUtopia: Dream General Robots in a City at Scale","date":"2024-07-15","arxiv_id":"2407.10943","repositories_listed":1,"syntology":null},{"url":"/paper/think-on-graph-2-0-deep-and-interpretable","slug":"think-on-graph-2-0-deep-and-interpretable","title":"Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation","date":"2024-07-15","arxiv_id":"2407.10805","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/think-on-graph-2-0-deep-and-interpretable#ran","syntology_url":"https://syntology.ai/paper/2407.10805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10805"}},"official":{"repos":["idea-finai/tog-2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/when-ai-meets-finance-stockagent-large","slug":"when-ai-meets-finance-stockagent-large","title":"When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments","date":"2024-07-15","arxiv_id":"2407.18957","repositories_listed":1,"syntology":null},{"url":"/paper/practical-unlearning-for-large-language","slug":"practical-unlearning-for-large-language","title":"On Large Language Model Continual Unlearning","date":"2024-07-14","arxiv_id":"2407.10223","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/practical-unlearning-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2407.10223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10223"}},"official":{"repos":["gcyzsl/o3-llm-unlearning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/global-local-collaborative-inference-with-llm","slug":"global-local-collaborative-inference-with-llm","title":"Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection","date":"2024-07-12","arxiv_id":"2407.08931","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"9 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/global-local-collaborative-inference-with-llm#ran","syntology_url":"https://syntology.ai/paper/2407.08931","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08931"}},"official":{"repos":["gradiustwinbee/glis"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/stepwise-verification-and-remediation-of","slug":"stepwise-verification-and-remediation-of","title":"Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors","date":"2024-07-12","arxiv_id":"2407.09136","repositories_listed":1,"syntology":null},{"url":"/paper/hypergraph-multi-modal-large-language-model","slug":"hypergraph-multi-modal-large-language-model","title":"Hypergraph Multi-modal Large Language Model: Exploiting EEG and Eye-tracking Modalities to Evaluate Heterogeneous Responses for Video Understanding","date":"2024-07-11","arxiv_id":"2407.08150","repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-large-language-models-into","slug":"incorporating-large-language-models-into","title":"Incorporating Large Language Models into Production Systems for Enhanced Task Automation and Flexibility","date":"2024-07-11","arxiv_id":"2407.08550","repositories_listed":1,"syntology":null},{"url":"/paper/seed-story-multimodal-long-story-generation","slug":"seed-story-multimodal-long-story-generation","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model","date":"2024-07-11","arxiv_id":"2407.08683","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":17,"phrase":"14 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; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/seed-story-multimodal-long-story-generation#ran","syntology_url":"https://syntology.ai/paper/2407.08683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08683"}},"official":{"repos":["tencentarc/seed-story"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/surpassing-cosine-similarity-for","slug":"surpassing-cosine-similarity-for","title":"Surpassing Cosine Similarity for Multidimensional Comparisons: Dimension Insensitive Euclidean Metric","date":"2024-07-11","arxiv_id":"2407.08623","repositories_listed":1,"syntology":null},{"url":"/paper/virtual-agents-for-alcohol-use-counseling","slug":"virtual-agents-for-alcohol-use-counseling","title":"Virtual Agents for Alcohol Use Counseling: Exploring LLM-Powered Motivational Interviewing","date":"2024-07-10","arxiv_id":"2407.08095","repositories_listed":1,"syntology":null},{"url":"/paper/chat-edit-3d-interactive-3d-scene-editing-via","slug":"chat-edit-3d-interactive-3d-scene-editing-via","title":"Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts","date":"2024-07-09","arxiv_id":"2407.06842","repositories_listed":1,"syntology":null},{"url":"/paper/fbi-llm-scaling-up-fully-binarized-llms-from","slug":"fbi-llm-scaling-up-fully-binarized-llms-from","title":"FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation","date":"2024-07-09","arxiv_id":"2407.07093","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":14,"phrase":"11 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fbi-llm-scaling-up-fully-binarized-llms-from#ran","syntology_url":"https://syntology.ai/paper/2407.07093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07093"}},"official":{"repos":["liqunma/fbi-llm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/debunc-mitigating-hallucinations-in-large","slug":"debunc-mitigating-hallucinations-in-large","title":"DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics","date":"2024-07-08","arxiv_id":"2407.06426","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"8 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/debunc-mitigating-hallucinations-in-large#ran","syntology_url":"https://syntology.ai/paper/2407.06426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06426"}},"official":{"repos":["lukeyoffe/debunc"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-recall-uncertainty-is","slug":"large-language-model-recall-uncertainty-is","title":"Large Language Model Recall Uncertainty is Modulated by the Fan Effect","date":"2024-07-08","arxiv_id":"2407.06349","repositories_listed":1,"syntology":null},{"url":"/paper/open-world-multi-label-text-classification","slug":"open-world-multi-label-text-classification","title":"Open-world Multi-label Text Classification with Extremely Weak Supervision","date":"2024-07-08","arxiv_id":"2407.05609","repositories_listed":1,"syntology":null},{"url":"/paper/psycollm-enhancing-llm-for-psychological","slug":"psycollm-enhancing-llm-for-psychological","title":"PsycoLLM: Enhancing LLM for Psychological Understanding and Evaluation","date":"2024-07-08","arxiv_id":"2407.05721","repositories_listed":1,"syntology":null},{"url":"/paper/cosyvoice-a-scalable-multilingual-zero-shot","slug":"cosyvoice-a-scalable-multilingual-zero-shot","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","date":"2024-07-07","arxiv_id":"2407.05407","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-hallucination-detection-through","slug":"enhancing-hallucination-detection-through","title":"Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses","date":"2024-07-07","arxiv_id":"2407.05474","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-hallucination-detection-through#ran","syntology_url":"https://syntology.ai/paper/2407.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05474"}},"official":{"repos":["asappresearch/halugen"],"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/large-language-models-are-good-medical-coders","slug":"large-language-models-are-good-medical-coders","title":"Large language models are good medical coders, if provided with tools","date":"2024-07-06","arxiv_id":"2407.12849","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/large-language-models-are-good-medical-coders#ran","syntology_url":"https://syntology.ai/paper/2407.12849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12849"}},"official":{"repos":["ainativehealth/goodmedicalcoder"],"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/shine-saliency-aware-hierarchical-negative","slug":"shine-saliency-aware-hierarchical-negative","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","date":"2024-07-06","arxiv_id":"2407.05118","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/shine-saliency-aware-hierarchical-negative#ran","syntology_url":"https://syntology.ai/paper/2407.05118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05118"}},"official":{"repos":["zxccade/shine"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/crafting-large-language-models-for-enhanced","slug":"crafting-large-language-models-for-enhanced","title":"Crafting Large Language Models for Enhanced Interpretability","date":"2024-07-05","arxiv_id":"2407.04307","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/crafting-large-language-models-for-enhanced#ran","syntology_url":"https://syntology.ai/paper/2407.04307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04307"}},"official":null}}],"record_sha256":"5d59ca2eea14c09a81d691302d1251587d38d778e5432cf1900e679845e04155","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}