{"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/question-answering/papers/21","list_of":"/task/question-answering","task":"Question Answering","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":21,"pages_in_order":109,"rows_per_page":100,"rows":[2001,2100],"of":10817,"counts":{"archive_papers_tagged":10817,"with_a_code_link":4171,"where_syntology_ran_a_sample":1274,"not_listed_spam_title":0,"listed":10817,"listed_where_code_ran":1274,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1073,"every_run_a_failure_of_syntologys_instrument":201,"listed_with_a_run_with_no_instrument_failure":1073,"listed_every_run_a_failure_of_syntologys_instrument":201,"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/question-answering","prev":"/task/question-answering/papers/20","next":"/task/question-answering/papers/22","papers":[{"url":"/paper/artquest-countering-hidden-language-biases-in","slug":"artquest-countering-hidden-language-biases-in","title":"ArtQuest: Countering Hidden Language Biases in ArtVQA","date":"2024-01-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-natural-language-understanding-with","slug":"improving-natural-language-understanding-with","title":"ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion","date":"2024-01-04","arxiv_id":"2401.02993","repositories_listed":1,"syntology":null},{"url":"/paper/location-aware-modular-biencoder-for-tourism","slug":"location-aware-modular-biencoder-for-tourism","title":"Location Aware Modular Biencoder for Tourism Question Answering","date":"2024-01-04","arxiv_id":"2401.02187","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-large-language-models-in-semantic","slug":"evaluating-large-language-models-in-semantic","title":"Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs","date":"2024-01-03","arxiv_id":"2401.01711","repositories_listed":1,"syntology":null},{"url":"/paper/glance-and-focus-memory-prompting-for-multi-1","slug":"glance-and-focus-memory-prompting-for-multi-1","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","date":"2024-01-03","arxiv_id":"2401.01529","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_constructed":2,"n_ran_checked":14,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":13,"n_pointer_only":7,"phrase":"14 ran (of which 2 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/glance-and-focus-memory-prompting-for-multi-1#ran","syntology_url":"https://syntology.ai/paper/2401.01529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01529"}},"official":{"repos":["byz0e/glance-focus"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":2,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/gpt-4v-ision-is-a-generalist-web-agent-if","slug":"gpt-4v-ision-is-a-generalist-web-agent-if","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","date":"2024-01-03","arxiv_id":"2401.01614","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":14,"phrase":"13 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gpt-4v-ision-is-a-generalist-web-agent-if#ran","syntology_url":"https://syntology.ai/paper/2401.01614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01614"}},"official":{"repos":["osu-nlp-group/seeact"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sports-qa-a-large-scale-video-question","slug":"sports-qa-a-large-scale-video-question","title":"Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports","date":"2024-01-03","arxiv_id":"2401.01505","repositories_listed":1,"syntology":null},{"url":"/paper/ll3da-visual-interactive-instruction-tuning-1","slug":"ll3da-visual-interactive-instruction-tuning-1","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/geogalactica-a-scientific-large-language","slug":"geogalactica-a-scientific-large-language","title":"GeoGalactica: A Scientific Large Language Model in Geoscience","date":"2023-12-31","arxiv_id":"2401.00434","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-the-impact-of-false-negatives-in","slug":"mitigating-the-impact-of-false-negatives-in","title":"Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence Regularization","date":"2023-12-30","arxiv_id":"2401.00165","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 4 unverified","sample_list":"/paper/mitigating-the-impact-of-false-negatives-in#ran","syntology_url":"https://syntology.ai/paper/2401.00165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00165"}},"official":{"repos":["wangskygit/passage-sieve"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simple-llm-framework-for-long-range-video","slug":"a-simple-llm-framework-for-long-range-video","title":"A Simple LLM Framework for Long-Range Video Question-Answering","date":"2023-12-28","arxiv_id":"2312.17235","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/a-simple-llm-framework-for-long-range-video#ran","syntology_url":"https://syntology.ai/paper/2312.17235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17235"}},"official":{"repos":["ceezh/llovi"],"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/secqa-a-concise-question-answering-dataset","slug":"secqa-a-concise-question-answering-dataset","title":"SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer Security","date":"2023-12-26","arxiv_id":"2312.15838","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/secqa-a-concise-question-answering-dataset#ran","syntology_url":"https://syntology.ai/paper/2312.15838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15838"}},"official":{"repos":["zefang-liu/lm-evaluation-harness"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/supervised-knowledge-makes-large-language","slug":"supervised-knowledge-makes-large-language","title":"Supervised Knowledge Makes Large Language Models Better In-context Learners","date":"2023-12-26","arxiv_id":"2312.15918","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/supervised-knowledge-makes-large-language#ran","syntology_url":"https://syntology.ai/paper/2312.15918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15918"}},"official":{"repos":["yanglinyi/supervised-knowledge-makes-large-language-models-better-in-context-learners"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pokemqa-programmable-knowledge-editing-for","slug":"pokemqa-programmable-knowledge-editing-for","title":"PokeMQA: Programmable knowledge editing for Multi-hop Question Answering","date":"2023-12-23","arxiv_id":"2312.15194","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pokemqa-programmable-knowledge-editing-for#ran","syntology_url":"https://syntology.ai/paper/2312.15194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15194"}},"official":{"repos":["hengrui-gu/pokemqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reverse-multi-choice-dialogue-commonsense","slug":"reverse-multi-choice-dialogue-commonsense","title":"Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thought","date":"2023-12-23","arxiv_id":"2312.15291","repositories_listed":1,"syntology":null},{"url":"/paper/numerical-reasoning-for-financial-reports","slug":"numerical-reasoning-for-financial-reports","title":"Numerical Reasoning for Financial Reports","date":"2023-12-22","arxiv_id":"2312.14870","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-unified-multimodal-reasoning","slug":"towards-a-unified-multimodal-reasoning","title":"Towards a Unified Multimodal Reasoning Framework","date":"2023-12-22","arxiv_id":"2312.15021","repositories_listed":1,"syntology":null},{"url":"/paper/vcoder-versatile-vision-encoders-for","slug":"vcoder-versatile-vision-encoders-for","title":"VCoder: Versatile Vision Encoders for Multimodal Large Language Models","date":"2023-12-21","arxiv_id":"2312.14233","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vcoder-versatile-vision-encoders-for#ran","syntology_url":"https://syntology.ai/paper/2312.14233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14233"}},"official":{"repos":["shi-labs/vcoder"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dspy-assertions-computational-constraints-for","slug":"dspy-assertions-computational-constraints-for","title":"DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines","date":"2023-12-20","arxiv_id":"2312.13382","repositories_listed":1,"syntology":null},{"url":"/paper/generative-multimodal-models-are-in-context","slug":"generative-multimodal-models-are-in-context","title":"Generative Multimodal Models are In-Context Learners","date":"2023-12-20","arxiv_id":"2312.13286","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/generative-multimodal-models-are-in-context#ran","syntology_url":"https://syntology.ai/paper/2312.13286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13286"}},"official":{"repos":["baaivision/emu"],"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/lookahead-an-inference-acceleration-framework","slug":"lookahead-an-inference-acceleration-framework","title":"Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy","date":"2023-12-20","arxiv_id":"2312.12728","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/lookahead-an-inference-acceleration-framework#ran","syntology_url":"https://syntology.ai/paper/2312.12728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12728"}},"official":{"repos":["alipay/PainlessInferenceAcceleration"],"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/object-attribute-matters-in-visual-question","slug":"object-attribute-matters-in-visual-question","title":"Object Attribute Matters in Visual Question Answering","date":"2023-12-20","arxiv_id":"2401.09442","repositories_listed":1,"syntology":null},{"url":"/paper/object-aware-adaptive-positivity-learning-for","slug":"object-aware-adaptive-positivity-learning-for","title":"Object-aware Adaptive-Positivity Learning for Audio-Visual Question Answering","date":"2023-12-20","arxiv_id":"2312.12816","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/object-aware-adaptive-positivity-learning-for#ran","syntology_url":"https://syntology.ai/paper/2312.12816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12816"}},"official":{"repos":["zhangbin-ai/apl"],"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/earthvqa-towards-queryable-earth-via","slug":"earthvqa-towards-queryable-earth-via","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","date":"2023-12-19","arxiv_id":"2312.12222","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":6,"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/earthvqa-towards-queryable-earth-via#ran","syntology_url":"https://syntology.ai/paper/2312.12222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12222"}},"official":{"repos":["Junjue-Wang/EarthVQA"],"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/melo-enhancing-model-editing-with-neuron","slug":"melo-enhancing-model-editing-with-neuron","title":"MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA","date":"2023-12-19","arxiv_id":"2312.11795","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/melo-enhancing-model-editing-with-neuron#ran","syntology_url":"https://syntology.ai/paper/2312.11795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11795"}},"official":{"repos":["bruthyu/melo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-early-detection-of-hallucinations-in","slug":"on-early-detection-of-hallucinations-in","title":"On Early Detection of Hallucinations in Factual Question Answering","date":"2023-12-19","arxiv_id":"2312.14183","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/on-early-detection-of-hallucinations-in#ran","syntology_url":"https://syntology.ai/paper/2312.14183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14183"}},"official":{"repos":["amazon-science/llm-hallucinations-factual-qa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/relation-aware-question-answering-for","slug":"relation-aware-question-answering-for","title":"Relation-Aware Question Answering for Heterogeneous Knowledge Graphs","date":"2023-12-19","arxiv_id":"2312.11922","repositories_listed":1,"syntology":null},{"url":"/paper/vqa4cir-boosting-composed-image-retrieval","slug":"vqa4cir-boosting-composed-image-retrieval","title":"VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering","date":"2023-12-19","arxiv_id":"2312.12273","repositories_listed":1,"syntology":null},{"url":"/paper/haar-text-conditioned-generative-model-of-3d","slug":"haar-text-conditioned-generative-model-of-3d","title":"HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles","date":"2023-12-18","arxiv_id":"2312.11666","repositories_listed":1,"syntology":null},{"url":"/paper/osmlocator-locating-overlapping-scatter-marks","slug":"osmlocator-locating-overlapping-scatter-marks","title":"OsmLocator: locating overlapping scatter marks with a non-training generative perspective","date":"2023-12-18","arxiv_id":"2312.11146","repositories_listed":1,"syntology":null},{"url":"/paper/p-laplacian-adaptation-for-generative-pre","slug":"p-laplacian-adaptation-for-generative-pre","title":"p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models","date":"2023-12-17","arxiv_id":"2312.10613","repositories_listed":1,"syntology":null},{"url":"/paper/llm-sql-solver-can-llms-determine-sql","slug":"llm-sql-solver-can-llms-determine-sql","title":"LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?","date":"2023-12-16","arxiv_id":"2312.10321","repositories_listed":1,"syntology":null},{"url":"/paper/do-text-simplification-systems-preserve","slug":"do-text-simplification-systems-preserve","title":"Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension","date":"2023-12-15","arxiv_id":"2312.10126","repositories_listed":1,"syntology":null},{"url":"/paper/extending-context-window-of-large-language-1","slug":"extending-context-window-of-large-language-1","title":"Extending Context Window of Large Language Models via Semantic Compression","date":"2023-12-15","arxiv_id":"2312.09571","repositories_listed":1,"syntology":null},{"url":"/paper/pipeline-and-dataset-generation-for-automated","slug":"pipeline-and-dataset-generation-for-automated","title":"Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language","date":"2023-12-15","arxiv_id":"2312.10171","repositories_listed":1,"syntology":null},{"url":"/paper/privacy-aware-document-visual-question","slug":"privacy-aware-document-visual-question","title":"Privacy-Aware Document Visual Question Answering","date":"2023-12-15","arxiv_id":"2312.10108","repositories_listed":1,"syntology":null},{"url":"/paper/rjua-qa-a-comprehensive-qa-dataset-for","slug":"rjua-qa-a-comprehensive-qa-dataset-for","title":"RJUA-QA: A Comprehensive QA Dataset for Urology","date":"2023-12-15","arxiv_id":"2312.09785","repositories_listed":1,"syntology":null},{"url":"/paper/wordscape-a-pipeline-to-extract-multilingual-1","slug":"wordscape-a-pipeline-to-extract-multilingual-1","title":"WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data","date":"2023-12-15","arxiv_id":"2312.10188","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/wordscape-a-pipeline-to-extract-multilingual-1#ran","syntology_url":"https://syntology.ai/paper/2312.10188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10188"}},"official":{"repos":["DS3Lab/WordScape"],"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/vl-gpt-a-generative-pre-trained-transformer","slug":"vl-gpt-a-generative-pre-trained-transformer","title":"VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation","date":"2023-12-14","arxiv_id":"2312.09251","repositories_listed":1,"syntology":null},{"url":"/paper/look-before-you-leap-a-universal-emergent","slug":"look-before-you-leap-a-universal-emergent","title":"Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models","date":"2023-12-13","arxiv_id":"2312.10091","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":11,"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) · 6 unverified","sample_list":"/paper/look-before-you-leap-a-universal-emergent#ran","syntology_url":"https://syntology.ai/paper/2312.10091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10091"}},"official":{"repos":["avariengien/causal-checker"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/vlap-efficient-video-language-alignment-via","slug":"vlap-efficient-video-language-alignment-via","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","date":"2023-12-13","arxiv_id":"2312.08367","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vlap-efficient-video-language-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2312.08367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08367"}},"official":{"repos":["xijun-cs/vila"],"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/image-content-generation-with-causal","slug":"image-content-generation-with-causal","title":"Image Content Generation with Causal Reasoning","date":"2023-12-12","arxiv_id":"2312.07132","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/image-content-generation-with-causal#ran","syntology_url":"https://syntology.ai/paper/2312.07132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07132"}},"official":{"repos":["ieit-agi/mix-shannon"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/safety-alignment-in-nlp-tasks-weakly-aligned","slug":"safety-alignment-in-nlp-tasks-weakly-aligned","title":"Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack","date":"2023-12-12","arxiv_id":"2312.06924","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safety-alignment-in-nlp-tasks-weakly-aligned#ran","syntology_url":"https://syntology.ai/paper/2312.06924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06924"}},"official":{"repos":["fyyfu/safetyalignnlp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/genixer-empowering-multimodal-large-language","slug":"genixer-empowering-multimodal-large-language","title":"Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator","date":"2023-12-11","arxiv_id":"2312.06731","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/genixer-empowering-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2312.06731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06731"}},"official":{"repos":["zhaohengyuan1/genixer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/nuscenes-mqa-integrated-evaluation-of","slug":"nuscenes-mqa-integrated-evaluation-of","title":"NuScenes-MQA: Integrated Evaluation of Captions and QA for Autonomous Driving Datasets using Markup Annotations","date":"2023-12-11","arxiv_id":"2312.06352","repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-anticipatory-text-generation-a","slug":"unlocking-anticipatory-text-generation-a","title":"Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding","date":"2023-12-11","arxiv_id":"2312.06149","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unlocking-anticipatory-text-generation-a#ran","syntology_url":"https://syntology.ai/paper/2312.06149","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06149"}},"official":{"repos":["SalesforceAIResearch/Unlocking-TextGen"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/unifying-text-tables-and-images-for","slug":"unifying-text-tables-and-images-for","title":"Unifying Text, Tables, and Images for Multimodal Question Answering","date":"2023-12-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gym-at-quran-qa-2023-shared-task-multi-task","slug":"gym-at-quran-qa-2023-shared-task-multi-task","title":"GYM at Qur’an QA 2023 Shared Task: Multi-Task Transfer Learning for Quranic Passage Retrieval and Question Answering with Large Language Models","date":"2023-12-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/language-model-knowledge-distillation-for","slug":"language-model-knowledge-distillation-for","title":"Language Model Knowledge Distillation for Efficient Question Answering in Spanish","date":"2023-12-07","arxiv_id":"2312.04193","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/language-model-knowledge-distillation-for#ran","syntology_url":"https://syntology.ai/paper/2312.04193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04193"}},"official":{"repos":["adrianbzg/tinyroberta-distillation-qa-es"],"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/lifelongmemory-leveraging-llms-for-answering","slug":"lifelongmemory-leveraging-llms-for-answering","title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","date":"2023-12-07","arxiv_id":"2312.05269","repositories_listed":1,"syntology":null},{"url":"/paper/language-informed-visual-concept-learning","slug":"language-informed-visual-concept-learning","title":"Language-Informed Visual Concept Learning","date":"2023-12-06","arxiv_id":"2312.03587","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/language-informed-visual-concept-learning#ran","syntology_url":"https://syntology.ai/paper/2312.03587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03587"}},"official":{"repos":["sharonal10/langint"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/onellm-one-framework-to-align-all-modalities","slug":"onellm-one-framework-to-align-all-modalities","title":"OneLLM: One Framework to Align All Modalities with Language","date":"2023-12-06","arxiv_id":"2312.03700","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/onellm-one-framework-to-align-all-modalities#ran","syntology_url":"https://syntology.ai/paper/2312.03700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03700"}},"official":{"repos":["csuhan/onellm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/let-the-llms-talk-simulating-human-to-human","slug":"let-the-llms-talk-simulating-human-to-human","title":"Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions","date":"2023-12-05","arxiv_id":"2312.02913","repositories_listed":1,"syntology":null},{"url":"/paper/chatgpt-as-a-math-questioner-evaluating","slug":"chatgpt-as-a-math-questioner-evaluating","title":"ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Questions","date":"2023-12-04","arxiv_id":"2312.01661","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-dependencies-in-fact-editing-for","slug":"evaluating-dependencies-in-fact-editing-for","title":"Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness","date":"2023-12-04","arxiv_id":"2312.01858","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/evaluating-dependencies-in-fact-editing-for#ran","syntology_url":"https://syntology.ai/paper/2312.01858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01858"}},"official":{"repos":["mcgill-nlp/logicalknowedit"],"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/gnn2r-weakly-supervised-rationale-providing","slug":"gnn2r-weakly-supervised-rationale-providing","title":"GNN2R: Weakly-Supervised Rationale-Providing Question Answering over Knowledge Graphs","date":"2023-12-04","arxiv_id":"2312.02317","repositories_listed":1,"syntology":null},{"url":"/paper/good-questions-help-zero-shot-image-reasoning","slug":"good-questions-help-zero-shot-image-reasoning","title":"Good Questions Help Zero-Shot Image Reasoning","date":"2023-12-04","arxiv_id":"2312.01598","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-configure-good-in-context-sequence-for","slug":"how-to-configure-good-in-context-sequence-for","title":"How to Configure Good In-Context Sequence for Visual Question Answering","date":"2023-12-04","arxiv_id":"2312.01571","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-to-configure-good-in-context-sequence-for#ran","syntology_url":"https://syntology.ai/paper/2312.01571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01571"}},"official":{"repos":["garyjiajia/ofv2_icl_vqa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/recursive-visual-programming","slug":"recursive-visual-programming","title":"Recursive Visual Programming","date":"2023-12-04","arxiv_id":"2312.02249","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":13,"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) · 2 unverified","sample_list":"/paper/recursive-visual-programming#ran","syntology_url":"https://syntology.ai/paper/2312.02249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02249"}},"official":{"repos":["para-lost/rvp"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-background-knowledge-gaps-in","slug":"bridging-background-knowledge-gaps-in","title":"Bridging Background Knowledge Gaps in Translation with Automatic Explicitation","date":"2023-12-03","arxiv_id":"2312.01308","repositories_listed":1,"syntology":null},{"url":"/paper/nlebench-norglm-a-comprehensive-empirical","slug":"nlebench-norglm-a-comprehensive-empirical","title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","date":"2023-12-03","arxiv_id":"2312.01314","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/nlebench-norglm-a-comprehensive-empirical#ran","syntology_url":"https://syntology.ai/paper/2312.01314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01314"}},"official":{"repos":["smartmedia-ai/norglm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/harnessing-the-power-of-prompt-based","slug":"harnessing-the-power-of-prompt-based","title":"Harnessing the Power of Prompt-based Techniques for Generating School-Level Questions using Large Language Models","date":"2023-12-02","arxiv_id":"2312.01032","repositories_listed":1,"syntology":null},{"url":"/paper/ll3da-visual-interactive-instruction-tuning","slug":"ll3da-visual-interactive-instruction-tuning","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","date":"2023-11-30","arxiv_id":"2311.18651","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":5,"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/ll3da-visual-interactive-instruction-tuning#ran","syntology_url":"https://syntology.ai/paper/2311.18651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18651"}},"official":{"repos":["open3da/ll3da"],"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/reinforcement-replaces-supervision-query","slug":"reinforcement-replaces-supervision-query","title":"Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement Learning","date":"2023-11-29","arxiv_id":"2311.17514","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-guided-global-memory-improves","slug":"uncertainty-guided-global-memory-improves","title":"Uncertainty Guided Global Memory Improves Multi-Hop Question Answering","date":"2023-11-29","arxiv_id":"2311.18151","repositories_listed":1,"syntology":null},{"url":"/paper/plug-and-play-dense-label-free-extraction-of","slug":"plug-and-play-dense-label-free-extraction-of","title":"Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models","date":"2023-11-28","arxiv_id":"2311.17095","repositories_listed":1,"syntology":null},{"url":"/paper/can-vision-language-models-think-from-a-first","slug":"can-vision-language-models-think-from-a-first","title":"EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models","date":"2023-11-27","arxiv_id":"2311.15596","repositories_listed":1,"syntology":null},{"url":"/paper/cerbero-7b-a-leap-forward-in-language","slug":"cerbero-7b-a-leap-forward-in-language","title":"Cerbero-7B: A Leap Forward in Language-Specific LLMs Through Enhanced Chat Corpus Generation and Evaluation","date":"2023-11-27","arxiv_id":"2311.15698","repositories_listed":1,"syntology":null},{"url":"/paper/fully-authentic-visual-question-answering","slug":"fully-authentic-visual-question-answering","title":"Fully Authentic Visual Question Answering Dataset from Online Communities","date":"2023-11-27","arxiv_id":"2311.15562","repositories_listed":1,"syntology":null},{"url":"/paper/increasing-coverage-and-precision-of-textual","slug":"increasing-coverage-and-precision-of-textual","title":"Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs","date":"2023-11-27","arxiv_id":"2311.15781","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/increasing-coverage-and-precision-of-textual#ran","syntology_url":"https://syntology.ai/paper/2311.15781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15781"}},"official":{"repos":["apple/ml-kge"],"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/llmga-multimodal-large-language-model-based","slug":"llmga-multimodal-large-language-model-based","title":"LLMGA: Multimodal Large Language Model based Generation Assistant","date":"2023-11-27","arxiv_id":"2311.16500","repositories_listed":1,"syntology":null},{"url":"/paper/meditron-70b-scaling-medical-pretraining-for","slug":"meditron-70b-scaling-medical-pretraining-for","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","date":"2023-11-27","arxiv_id":"2311.16079","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/meditron-70b-scaling-medical-pretraining-for#ran","syntology_url":"https://syntology.ai/paper/2311.16079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16079"}},"official":{"repos":["epfllm/meditron"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/video-bench-a-comprehensive-benchmark-and","slug":"video-bench-a-comprehensive-benchmark-and","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","date":"2023-11-27","arxiv_id":"2311.16103","repositories_listed":1,"syntology":null},{"url":"/paper/autoeval-video-an-automatic-benchmark-for","slug":"autoeval-video-an-automatic-benchmark-for","title":"AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering","date":"2023-11-25","arxiv_id":"2311.14906","repositories_listed":1,"syntology":null},{"url":"/paper/geochat-grounded-large-vision-language-model","slug":"geochat-grounded-large-vision-language-model","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","date":"2023-11-24","arxiv_id":"2311.15826","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/geochat-grounded-large-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2311.15826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15826"}},"official":{"repos":["mbzuai-oryx/geochat"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/pg-video-llava-pixel-grounding-large-video","slug":"pg-video-llava-pixel-grounding-large-video","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","date":"2023-11-22","arxiv_id":"2311.13435","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pg-video-llava-pixel-grounding-large-video#ran","syntology_url":"https://syntology.ai/paper/2311.13435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13435"}},"official":{"repos":["mbzuai-oryx/video-llava"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/speak-like-a-native-prompting-large-language","slug":"speak-like-a-native-prompting-large-language","title":"AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations","date":"2023-11-22","arxiv_id":"2311.13538","repositories_listed":1,"syntology":null},{"url":"/paper/vamos-versatile-action-models-for-video","slug":"vamos-versatile-action-models-for-video","title":"Vamos: Versatile Action Models for Video Understanding","date":"2023-11-22","arxiv_id":"2311.13627","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vamos-versatile-action-models-for-video#ran","syntology_url":"https://syntology.ai/paper/2311.13627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13627"}},"official":{"repos":["brown-palm/Vamos"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/csmed-bridging-the-dataset-gap-in-automated","slug":"csmed-bridging-the-dataset-gap-in-automated","title":"CSMeD: Bridging the Dataset Gap in Automated Citation Screening for Systematic Literature Reviews","date":"2023-11-21","arxiv_id":"2311.12474","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/csmed-bridging-the-dataset-gap-in-automated#ran","syntology_url":"https://syntology.ai/paper/2311.12474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12474"}},"official":{"repos":["wojciechkusa/systematic-review-datasets"],"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/nach0-multimodal-natural-and-chemical","slug":"nach0-multimodal-natural-and-chemical","title":"nach0: Multimodal Natural and Chemical Languages Foundation Model","date":"2023-11-21","arxiv_id":"2311.12410","repositories_listed":1,"syntology":null},{"url":"/paper/filling-the-image-information-gap-for-vqa","slug":"filling-the-image-information-gap-for-vqa","title":"Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions","date":"2023-11-20","arxiv_id":"2311.11598","repositories_listed":1,"syntology":null},{"url":"/paper/taiyi-a-bilingual-fine-tuned-large-language","slug":"taiyi-a-bilingual-fine-tuned-large-language","title":"Taiyi: A Bilingual Fine-Tuned Large Language Model for Diverse Biomedical Tasks","date":"2023-11-20","arxiv_id":"2311.11608","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-text-retrieval-with","slug":"towards-robust-text-retrieval-with","title":"Towards Robust Text Retrieval with Progressive Learning","date":"2023-11-20","arxiv_id":"2311.11691","repositories_listed":1,"syntology":null},{"url":"/paper/an-embodied-generalist-agent-in-3d-world","slug":"an-embodied-generalist-agent-in-3d-world","title":"An Embodied Generalist Agent in 3D World","date":"2023-11-18","arxiv_id":"2311.12871","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-embodied-generalist-agent-in-3d-world#ran","syntology_url":"https://syntology.ai/paper/2311.12871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12871"}},"official":{"repos":["embodied-generalist/embodied-generalist"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/crafting-in-context-examples-according-to-lms","slug":"crafting-in-context-examples-according-to-lms","title":"Crafting In-context Examples according to LMs' Parametric Knowledge","date":"2023-11-16","arxiv_id":"2311.09579","repositories_listed":1,"syntology":null},{"url":"/paper/fairytalecqa-integrating-a-commonsense","slug":"fairytalecqa-integrating-a-commonsense","title":"StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children's Story-Based Learning","date":"2023-11-16","arxiv_id":"2311.09756","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-llms-in-scholarly-knowledge-graph","slug":"leveraging-llms-in-scholarly-knowledge-graph","title":"Leveraging LLMs in Scholarly Knowledge Graph Question Answering","date":"2023-11-16","arxiv_id":"2311.09841","repositories_listed":1,"syntology":null},{"url":"/paper/performance-trade-offs-of-watermarking-large","slug":"performance-trade-offs-of-watermarking-large","title":"Downstream Trade-offs of a Family of Text Watermarks","date":"2023-11-16","arxiv_id":"2311.09816","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/performance-trade-offs-of-watermarking-large#ran","syntology_url":"https://syntology.ai/paper/2311.09816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09816"}},"official":{"repos":["flair-iisc/watermark_tradeoffs"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prudent-silence-or-foolish-babble-examining","slug":"prudent-silence-or-foolish-babble-examining","title":"Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge","date":"2023-11-16","arxiv_id":"2311.09731","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prudent-silence-or-foolish-babble-examining#ran","syntology_url":"https://syntology.ai/paper/2311.09731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09731"}},"official":{"repos":["genglinliu/unknownbench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sqatin-supervised-instruction-tuning-meets","slug":"sqatin-supervised-instruction-tuning-meets","title":"SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU","date":"2023-11-16","arxiv_id":"2311.09502","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-temporal-reasoning-of-large","slug":"towards-robust-temporal-reasoning-of-large","title":"Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning","date":"2023-11-16","arxiv_id":"2311.09821","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"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) · 2 unverified","sample_list":"/paper/towards-robust-temporal-reasoning-of-large#ran","syntology_url":"https://syntology.ai/paper/2311.09821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09821"}},"official":{"repos":["nusnlp/complex-tr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/you-don-t-need-a-personality-test-to-know","slug":"you-don-t-need-a-personality-test-to-know","title":"You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments","date":"2023-11-16","arxiv_id":"2311.09718","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"8 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; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/you-don-t-need-a-personality-test-to-know#ran","syntology_url":"https://syntology.ai/paper/2311.09718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09718"}},"official":{"repos":["orange0629/llm-personas"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/attribute-diversity-determines-the","slug":"attribute-diversity-determines-the","title":"Attribute Diversity Determines the Systematicity Gap in VQA","date":"2023-11-15","arxiv_id":"2311.08695","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":6,"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/attribute-diversity-determines-the#ran","syntology_url":"https://syntology.ai/paper/2311.08695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08695"}},"official":{"repos":["ikb-a/systematicity-gap-in-vqa"],"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/combining-transfer-learning-with-in-context","slug":"combining-transfer-learning-with-in-context","title":"Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning","date":"2023-11-15","arxiv_id":"2311.08894","repositories_listed":1,"syntology":null},{"url":"/paper/contradoc-understanding-self-contradictions","slug":"contradoc-understanding-self-contradictions","title":"ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models","date":"2023-11-15","arxiv_id":"2311.09182","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contradoc-understanding-self-contradictions#ran","syntology_url":"https://syntology.ai/paper/2311.09182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09182"}},"official":{"repos":["ddhruvkr/contradoc"],"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/improving-zero-shot-visual-question-answering","slug":"improving-zero-shot-visual-question-answering","title":"Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts","date":"2023-11-15","arxiv_id":"2311.09050","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-over-description-logic-based","slug":"reasoning-over-description-logic-based","title":"Transformers in the Service of Description Logic-based Contexts","date":"2023-11-15","arxiv_id":"2311.08941","repositories_listed":1,"syntology":null},{"url":"/paper/rrescue-ranking-llm-responses-to-enhance","slug":"rrescue-ranking-llm-responses-to-enhance","title":"Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation","date":"2023-11-15","arxiv_id":"2311.09136","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-knowledge-question-answering-via","slug":"temporal-knowledge-question-answering-via","title":"Temporal Knowledge Question Answering via Abstract Reasoning Induction","date":"2023-11-15","arxiv_id":"2311.09149","repositories_listed":1,"syntology":null},{"url":"/paper/videocon-robust-video-language-alignment-via","slug":"videocon-robust-video-language-alignment-via","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","date":"2023-11-15","arxiv_id":"2311.10111","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":1,"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/videocon-robust-video-language-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2311.10111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10111"}},"official":{"repos":["hritikbansal/videocon"],"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"]}}}],"record_sha256":"a191138c65a62df23a5354a0fe3712a9f8ffed1007cf7d11a0813b5e8e006acf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}