{"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/27","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":27,"pages_in_order":109,"rows_per_page":100,"rows":[2601,2700],"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/26","next":"/task/question-answering/papers/28","papers":[{"url":"/paper/extracting-victim-counts-from-text","slug":"extracting-victim-counts-from-text","title":"Extracting Victim Counts from Text","date":"2023-02-23","arxiv_id":"2302.12367","repositories_listed":1,"syntology":null},{"url":"/paper/fits-fine-grained-two-stage-training-for","slug":"fits-fine-grained-two-stage-training-for","title":"FiTs: Fine-grained Two-stage Training for Knowledge-aware Question Answering","date":"2023-02-23","arxiv_id":"2302.11799","repositories_listed":1,"syntology":null},{"url":"/paper/mfbe-leveraging-multi-field-information-of","slug":"mfbe-leveraging-multi-field-information-of","title":"MFBE: Leveraging Multi-Field Information of FAQs for Efficient Dense Retrieval","date":"2023-02-23","arxiv_id":"2302.11953","repositories_listed":1,"syntology":null},{"url":"/paper/connecting-vision-and-language-with-video","slug":"connecting-vision-and-language-with-video","title":"Connecting Vision and Language with Video Localized Narratives","date":"2023-02-22","arxiv_id":"2302.11217","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/connecting-vision-and-language-with-video#ran","syntology_url":"https://syntology.ai/paper/2302.11217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11217"}},"official":{"repos":["google/video-localized-narratives"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vinvl-l-enriching-visual-representation-with","slug":"vinvl-l-enriching-visual-representation-with","title":"VinVL+L: Enriching Visual Representation with Location Context in VQA","date":"2023-02-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/chatgpt-jack-of-all-trades-master-of-none","slug":"chatgpt-jack-of-all-trades-master-of-none","title":"ChatGPT: Jack of all trades, master of none","date":"2023-02-21","arxiv_id":"2302.10724","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/chatgpt-jack-of-all-trades-master-of-none#ran","syntology_url":"https://syntology.ai/paper/2302.10724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10724"}},"official":{"repos":["clarin-pl/chatgpt-evaluation-01-2023"],"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/zero-shot-information-extraction-via-chatting","slug":"zero-shot-information-extraction-via-chatting","title":"ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT","date":"2023-02-20","arxiv_id":"2302.10205","repositories_listed":1,"syntology":null},{"url":"/paper/can-chatgpt-understand-too-a-comparative","slug":"can-chatgpt-understand-too-a-comparative","title":"Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT","date":"2023-02-19","arxiv_id":"2302.10198","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-federated-learning-via-contrastive","slug":"multimodal-federated-learning-via-contrastive","title":"Multimodal Federated Learning via Contrastive Representation Ensemble","date":"2023-02-17","arxiv_id":"2302.08888","repositories_listed":1,"syntology":null},{"url":"/paper/towards-unifying-medical-vision-and-language","slug":"towards-unifying-medical-vision-and-language","title":"Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts","date":"2023-02-17","arxiv_id":"2302.08958","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-exemplars-for-in-context","slug":"compositional-exemplars-for-in-context","title":"Compositional Exemplars for In-context Learning","date":"2023-02-11","arxiv_id":"2302.05698","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"5 ran (of which 1 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) · 2 unverified","sample_list":"/paper/compositional-exemplars-for-in-context#ran","syntology_url":"https://syntology.ai/paper/2302.05698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.05698"}},"official":{"repos":["hkunlp/icl-ceil"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/differentiable-outlier-detection-enable","slug":"differentiable-outlier-detection-enable","title":"Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-02-11","arxiv_id":"2302.05608","repositories_listed":1,"syntology":null},{"url":"/paper/alloprof-a-new-french-question-answer","slug":"alloprof-a-new-french-question-answer","title":"Alloprof: a new French question-answer education dataset and its use in an information retrieval case study","date":"2023-02-10","arxiv_id":"2302.07738","repositories_listed":1,"syntology":null},{"url":"/paper/is-multi-modal-vision-supervision-beneficial","slug":"is-multi-modal-vision-supervision-beneficial","title":"Is Multimodal Vision Supervision Beneficial to Language?","date":"2023-02-10","arxiv_id":"2302.05016","repositories_listed":1,"syntology":null},{"url":"/paper/realistic-conversational-question-answering","slug":"realistic-conversational-question-answering","title":"Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement","date":"2023-02-10","arxiv_id":"2302.05137","repositories_listed":1,"syntology":null},{"url":"/paper/explanation-selection-using-unlabeled-data","slug":"explanation-selection-using-unlabeled-data","title":"Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting","date":"2023-02-09","arxiv_id":"2302.04813","repositories_listed":1,"syntology":null},{"url":"/paper/robust-question-answering-against","slug":"robust-question-answering-against","title":"Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study","date":"2023-02-09","arxiv_id":"2302.04618","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-end-to-end-video-question-answering","slug":"efficient-end-to-end-video-question-answering","title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer","date":"2023-02-04","arxiv_id":"2302.02136","repositories_listed":1,"syntology":null},{"url":"/paper/bioformer-an-efficient-transformer-language","slug":"bioformer-an-efficient-transformer-language","title":"Bioformer: an efficient transformer language model for biomedical text mining","date":"2023-02-03","arxiv_id":"2302.01588","repositories_listed":1,"syntology":null},{"url":"/paper/lampp-language-models-as-probabilistic-priors","slug":"lampp-language-models-as-probabilistic-priors","title":"LaMPP: Language Models as Probabilistic Priors for Perception and Action","date":"2023-02-03","arxiv_id":"2302.02801","repositories_listed":1,"syntology":null},{"url":"/paper/liquid-a-framework-for-list-question","slug":"liquid-a-framework-for-list-question","title":"LIQUID: A Framework for List Question Answering Dataset Generation","date":"2023-02-03","arxiv_id":"2302.01691","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/liquid-a-framework-for-list-question#ran","syntology_url":"https://syntology.ai/paper/2302.01691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.01691"}},"official":{"repos":["dmis-lab/liquid"],"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/language-quantized-autoencoders-towards-1","slug":"language-quantized-autoencoders-towards-1","title":"Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment","date":"2023-02-02","arxiv_id":"2302.00902","repositories_listed":1,"syntology":null},{"url":"/paper/multimodality-representation-learning-a","slug":"multimodality-representation-learning-a","title":"Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications","date":"2023-02-01","arxiv_id":"2302.00389","repositories_listed":1,"syntology":null},{"url":"/paper/faithful-chain-of-thought-reasoning","slug":"faithful-chain-of-thought-reasoning","title":"Faithful Chain-of-Thought Reasoning","date":"2023-01-31","arxiv_id":"2301.13379","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/faithful-chain-of-thought-reasoning#ran","syntology_url":"https://syntology.ai/paper/2301.13379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13379"}},"official":{"repos":["veronica320/faithful-cot"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/padl-language-directed-physics-based","slug":"padl-language-directed-physics-based","title":"PADL: Language-Directed Physics-Based Character Control","date":"2023-01-31","arxiv_id":"2301.13868","repositories_listed":1,"syntology":null},{"url":"/paper/heronet-a-hybrid-retrieval-generation-network","slug":"heronet-a-hybrid-retrieval-generation-network","title":"HeroNet: A Hybrid Retrieval-Generation Network for Conversational Bots","date":"2023-01-29","arxiv_id":"2301.12400","repositories_listed":1,"syntology":null},{"url":"/paper/binaryvqa-a-versatile-test-set-to-evaluate","slug":"binaryvqa-a-versatile-test-set-to-evaluate","title":"BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models","date":"2023-01-28","arxiv_id":"2301.12032","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-parsing-for-conversational-question","slug":"semantic-parsing-for-conversational-question","title":"Semantic Parsing for Conversational Question Answering over Knowledge Graphs","date":"2023-01-28","arxiv_id":"2301.12217","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparative-study-of-pretrained-language-1","slug":"a-comparative-study-of-pretrained-language-1","title":"A Comparative Study of Pretrained Language Models for Long Clinical Text","date":"2023-01-27","arxiv_id":"2301.11847","repositories_listed":1,"syntology":null},{"url":"/paper/thoughtsource-a-central-hub-for-large","slug":"thoughtsource-a-central-hub-for-large","title":"ThoughtSource: A central hub for large language model reasoning data","date":"2023-01-27","arxiv_id":"2301.11596","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/thoughtsource-a-central-hub-for-large#ran","syntology_url":"https://syntology.ai/paper/2301.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11596"}},"official":{"repos":["openbiolink/thoughtsource"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/videberta-a-powerful-pre-trained-language","slug":"videberta-a-powerful-pre-trained-language","title":"ViDeBERTa: A powerful pre-trained language model for Vietnamese","date":"2023-01-25","arxiv_id":"2301.10439","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videberta-a-powerful-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2301.10439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.10439"}},"official":{"repos":["hysonlab/videberta"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/primeqa-the-prime-repository-for-state-of-the","slug":"primeqa-the-prime-repository-for-state-of-the","title":"PrimeQA: The Prime Repository for State-of-the-Art Multilingual Question Answering Research and Development","date":"2023-01-23","arxiv_id":"2301.09715","repositories_listed":1,"syntology":null},{"url":"/paper/champion-solution-for-the-wsdm2023-toloka-vqa","slug":"champion-solution-for-the-wsdm2023-toloka-vqa","title":"Champion Solution for the WSDM2023 Toloka VQA Challenge","date":"2023-01-22","arxiv_id":"2301.09045","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-questions-for-zero-shot","slug":"weakly-supervised-questions-for-zero-shot","title":"Weakly-Supervised Questions for Zero-Shot Relation Extraction","date":"2023-01-21","arxiv_id":"2301.09640","repositories_listed":1,"syntology":null},{"url":"/paper/slidevqa-a-dataset-for-document-visual","slug":"slidevqa-a-dataset-for-document-visual","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","date":"2023-01-12","arxiv_id":"2301.04883","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-inverse-cloze-task-for-knowledge","slug":"multimodal-inverse-cloze-task-for-knowledge","title":"Multimodal Inverse Cloze Task for Knowledge-based Visual Question Answering","date":"2023-01-11","arxiv_id":"2301.04366","repositories_listed":1,"syntology":null},{"url":"/paper/mind-reasoning-manners-enhancing-type","slug":"mind-reasoning-manners-enhancing-type","title":"Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text","date":"2023-01-08","arxiv_id":"2301.02983","repositories_listed":1,"syntology":null},{"url":"/paper/adaptively-clustering-neighbor-elements-for","slug":"adaptively-clustering-neighbor-elements-for","title":"Adaptively Clustering Neighbor Elements for Image-Text Generation","date":"2023-01-05","arxiv_id":"2301.01955","repositories_listed":1,"syntology":null},{"url":"/paper/spring-situated-conversation-agent-pretrained","slug":"spring-situated-conversation-agent-pretrained","title":"SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph","date":"2023-01-05","arxiv_id":"2301.01949","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-alignment-and-mutual-masking","slug":"context-aware-alignment-and-mutual-masking","title":"Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-temporal-concurrency-for-video","slug":"exploring-temporal-concurrency-for-video","title":"Exploring Temporal Concurrency for Video-Language Representation Learning","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-effect-of-primitives-for","slug":"exploring-the-effect-of-primitives-for","title":"Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/toward-multi-granularity-decision-making","slug":"toward-multi-granularity-decision-making","title":"Toward Multi-Granularity Decision-Making: Explicit Visual Reasoning with Hierarchical Knowledge","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/variational-causal-inference-network-for","slug":"variational-causal-inference-network-for","title":"Variational Causal Inference Network for Explanatory Visual Question Answering","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vqacl-a-novel-visual-question-answering","slug":"vqacl-a-novel-visual-question-answering","title":"VQACL: A Novel Visual Question Answering Continual Learning Setting","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-with-retrieval-faithful-large","slug":"rethinking-with-retrieval-faithful-large","title":"Rethinking with Retrieval: Faithful Large Language Model Inference","date":"2022-12-31","arxiv_id":"2301.00303","repositories_listed":1,"syntology":null},{"url":"/paper/improving-complex-knowledge-base-question","slug":"improving-complex-knowledge-base-question","title":"Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment","date":"2022-12-26","arxiv_id":"2212.13036","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/improving-complex-knowledge-base-question#ran","syntology_url":"https://syntology.ai/paper/2212.13036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13036"}},"official":{"repos":["tttttttty/alcqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-encode-clinical","slug":"large-language-models-encode-clinical","title":"Large Language Models Encode Clinical Knowledge","date":"2022-12-26","arxiv_id":"2212.13138","repositories_listed":1,"syntology":null},{"url":"/paper/textbox-2-0-a-text-generation-library-with","slug":"textbox-2-0-a-text-generation-library-with","title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","date":"2022-12-26","arxiv_id":"2212.13005","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":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/textbox-2-0-a-text-generation-library-with#ran","syntology_url":"https://syntology.ai/paper/2212.13005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13005"}},"official":{"repos":["RUCAIBox/TextBox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/opt-iml-scaling-language-model-instruction","slug":"opt-iml-scaling-language-model-instruction","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","date":"2022-12-22","arxiv_id":"2212.12017","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-semantic-faithfulness-of-language","slug":"analyzing-semantic-faithfulness-of-language","title":"Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering","date":"2022-12-21","arxiv_id":"2212.10696","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-are-better-than-humans-at","slug":"language-models-are-better-than-humans-at","title":"Language models are better than humans at next-token prediction","date":"2022-12-21","arxiv_id":"2212.11281","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-models-are-better-than-humans-at#ran","syntology_url":"https://syntology.ai/paper/2212.11281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.11281"}},"official":{"repos":["FabienRoger/lm-game-analysis-main"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/parallel-context-windows-improve-in-context","slug":"parallel-context-windows-improve-in-context","title":"Parallel Context Windows for Large Language Models","date":"2022-12-21","arxiv_id":"2212.10947","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/parallel-context-windows-improve-in-context#ran","syntology_url":"https://syntology.ai/paper/2212.10947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10947"}},"official":{"repos":["AI21Labs/Parallel-Context-Windows"],"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/are-deep-neural-networks-smarter-than-second","slug":"are-deep-neural-networks-smarter-than-second","title":"Are Deep Neural Networks SMARTer than Second Graders?","date":"2022-12-20","arxiv_id":"2212.09993","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/are-deep-neural-networks-smarter-than-second#ran","syntology_url":"https://syntology.ai/paper/2212.09993","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09993"}},"official":{"repos":["merlresearch/SMART"],"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/defending-against-poisoning-attacks-in-open","slug":"defending-against-poisoning-attacks-in-open","title":"Defending Against Disinformation Attacks in Open-Domain Question Answering","date":"2022-12-20","arxiv_id":"2212.10002","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-fly-denoising-for-data-augmentation-in","slug":"on-the-fly-denoising-for-data-augmentation-in","title":"On-the-fly Denoising for Data Augmentation in Natural Language Understanding","date":"2022-12-20","arxiv_id":"2212.10558","repositories_listed":1,"syntology":null},{"url":"/paper/qa-2-question-answering-with-questionable","slug":"qa-2-question-answering-with-questionable","title":"(QA)$^2$: Question Answering with Questionable Assumptions","date":"2022-12-20","arxiv_id":"2212.10003","repositories_listed":1,"syntology":null},{"url":"/paper/wecheck-strong-factual-consistency-checker","slug":"wecheck-strong-factual-consistency-checker","title":"WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning","date":"2022-12-20","arxiv_id":"2212.10057","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-human-language-model-interaction","slug":"evaluating-human-language-model-interaction","title":"Evaluating Human-Language Model Interaction","date":"2022-12-19","arxiv_id":"2212.09746","repositories_listed":1,"syntology":null},{"url":"/paper/mist-multi-modal-iterative-spatial-temporal","slug":"mist-multi-modal-iterative-spatial-temporal","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","date":"2022-12-19","arxiv_id":"2212.09522","repositories_listed":1,"syntology":null},{"url":"/paper/source-free-domain-adaptation-for-question","slug":"source-free-domain-adaptation-for-question","title":"Source-Free Domain Adaptation for Question Answering with Masked Self-training","date":"2022-12-19","arxiv_id":"2212.09563","repositories_listed":1,"syntology":null},{"url":"/paper/tokenization-consistency-matters-for","slug":"tokenization-consistency-matters-for","title":"Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks","date":"2022-12-19","arxiv_id":"2212.09912","repositories_listed":1,"syntology":null},{"url":"/paper/visconde-multi-document-qa-with-gpt-3-and","slug":"visconde-multi-document-qa-with-gpt-3-and","title":"Visconde: Multi-document QA with GPT-3 and Neural Reranking","date":"2022-12-19","arxiv_id":"2212.09656","repositories_listed":1,"syntology":null},{"url":"/paper/can-retriever-augmented-language-models","slug":"can-retriever-augmented-language-models","title":"Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model","date":"2022-12-18","arxiv_id":"2212.09146","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-dense-retrieval-deserves-better","slug":"unsupervised-dense-retrieval-deserves-better","title":"AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation","date":"2022-12-17","arxiv_id":"2212.08841","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-multi-modal-and-multi-hop-question","slug":"enhancing-multi-modal-and-multi-hop-question","title":"Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation","date":"2022-12-16","arxiv_id":"2212.08632","repositories_listed":1,"syntology":null},{"url":"/paper/self-prompting-large-language-models-for-open","slug":"self-prompting-large-language-models-for-open","title":"Self-Prompting Large Language Models for Zero-Shot Open-Domain QA","date":"2022-12-16","arxiv_id":"2212.08635","repositories_listed":1,"syntology":null},{"url":"/paper/attributed-question-answering-evaluation-and","slug":"attributed-question-answering-evaluation-and","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","date":"2022-12-15","arxiv_id":"2212.08037","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":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/attributed-question-answering-evaluation-and#ran","syntology_url":"https://syntology.ai/paper/2212.08037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08037"}},"official":{"repos":["google-research-datasets/attributed-qa"],"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/image-and-language-understanding-from-pixels","slug":"image-and-language-understanding-from-pixels","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","date":"2022-12-15","arxiv_id":"2212.08045","repositories_listed":1,"syntology":null},{"url":"/paper/prompting-is-programming-a-query-language-for","slug":"prompting-is-programming-a-query-language-for","title":"Prompting Is Programming: A Query Language for Large Language Models","date":"2022-12-12","arxiv_id":"2212.06094","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-over-different-types-of-knowledge","slug":"reasoning-over-different-types-of-knowledge","title":"A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal","date":"2022-12-12","arxiv_id":"2212.05767","repositories_listed":1,"syntology":null},{"url":"/paper/reveal-retrieval-augmented-visual-language","slug":"reveal-retrieval-augmented-visual-language","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","date":"2022-12-10","arxiv_id":"2212.05221","repositories_listed":1,"syntology":null},{"url":"/paper/from-clozing-to-comprehending-retrofitting","slug":"from-clozing-to-comprehending-retrofitting","title":"From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader","date":"2022-12-09","arxiv_id":"2212.04755","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 2 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/from-clozing-to-comprehending-retrofitting#ran","syntology_url":"https://syntology.ai/paper/2212.04755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04755"}},"official":{"repos":["damo-nlp-sg/pmr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vindlu-a-recipe-for-effective-video-and","slug":"vindlu-a-recipe-for-effective-video-and","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","date":"2022-12-09","arxiv_id":"2212.05051","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-latent-knowledge-in-language","slug":"discovering-latent-knowledge-in-language","title":"Discovering Latent Knowledge in Language Models Without Supervision","date":"2022-12-07","arxiv_id":"2212.03827","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/discovering-latent-knowledge-in-language#ran","syntology_url":"https://syntology.ai/paper/2212.03827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03827"}},"official":{"repos":["collin-burns/discovering_latent_knowledge"],"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/hierarchical-multimodal-transformers-for","slug":"hierarchical-multimodal-transformers-for","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","date":"2022-12-07","arxiv_id":"2212.05935","repositories_listed":1,"syntology":null},{"url":"/paper/learning-action-effect-dynamics-for","slug":"learning-action-effect-dynamics-for","title":"Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task","date":"2022-12-07","arxiv_id":"2212.03866","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-as-attention-end-to-end-learning-of","slug":"retrieval-as-attention-end-to-end-learning-of","title":"Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer","date":"2022-12-05","arxiv_id":"2212.02027","repositories_listed":1,"syntology":null},{"url":"/paper/utilizing-background-knowledge-for-robust","slug":"utilizing-background-knowledge-for-robust","title":"Utilizing Background Knowledge for Robust Reasoning over Traffic Situations","date":"2022-12-04","arxiv_id":"2212.07798","repositories_listed":1,"syntology":null},{"url":"/paper/visual-question-answering-from-another-1","slug":"visual-question-answering-from-another-1","title":"Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests","date":"2022-12-03","arxiv_id":"2212.01639","repositories_listed":1,"syntology":null},{"url":"/paper/nonparametric-masked-language-modeling","slug":"nonparametric-masked-language-modeling","title":"Nonparametric Masked Language Modeling","date":"2022-12-02","arxiv_id":"2212.01349","repositories_listed":1,"syntology":null},{"url":"/paper/relation-aware-language-graph-transformer-for","slug":"relation-aware-language-graph-transformer-for","title":"Relation-Aware Language-Graph Transformer for Question Answering","date":"2022-12-02","arxiv_id":"2212.00975","repositories_listed":1,"syntology":null},{"url":"/paper/unikgqa-unified-retrieval-and-reasoning-for","slug":"unikgqa-unified-retrieval-and-reasoning-for","title":"UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph","date":"2022-12-02","arxiv_id":"2212.00959","repositories_listed":1,"syntology":{"n":17,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":8,"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) · 8 unverified","sample_list":"/paper/unikgqa-unified-retrieval-and-reasoning-for#ran","syntology_url":"https://syntology.ai/paper/2212.00959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00959"}},"official":{"repos":["rucaibox/unikgqa"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/a-sequential-flow-control-framework-for-multi","slug":"a-sequential-flow-control-framework-for-multi","title":"A Sequential Flow Control Framework for Multi-hop Knowledge Base Question Answering","date":"2022-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/analogical-math-word-problems-solving-with","slug":"analogical-math-word-problems-solving-with","title":"Analogical Math Word Problems Solving with Enhanced Problem-Solution Association","date":"2022-12-01","arxiv_id":"2212.00837","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-select-from-multiple-options","slug":"learning-to-select-from-multiple-options","title":"Learning to Select from Multiple Options","date":"2022-12-01","arxiv_id":"2212.00301","repositories_listed":1,"syntology":null},{"url":"/paper/nir-prompt-a-multi-task-generalized-neural","slug":"nir-prompt-a-multi-task-generalized-neural","title":"NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework","date":"2022-12-01","arxiv_id":"2212.00229","repositories_listed":1,"syntology":null},{"url":"/paper/a-pipeline-for-generating-annotating-and","slug":"a-pipeline-for-generating-annotating-and","title":"A Pipeline for Generating, Annotating and Employing Synthetic Data for Real World Question Answering","date":"2022-11-30","arxiv_id":"2211.16971","repositories_listed":1,"syntology":null},{"url":"/paper/aioner-all-in-one-scheme-based-biomedical","slug":"aioner-all-in-one-scheme-based-biomedical","title":"AIONER: All-in-one scheme-based biomedical named entity recognition using deep learning","date":"2022-11-30","arxiv_id":"2211.16944","repositories_listed":1,"syntology":null},{"url":"/paper/crepe-open-domain-question-answering-with","slug":"crepe-open-domain-question-answering-with","title":"CREPE: Open-Domain Question Answering with False Presuppositions","date":"2022-11-30","arxiv_id":"2211.17257","repositories_listed":1,"syntology":null},{"url":"/paper/weisfeiler-and-leman-go-relational","slug":"weisfeiler-and-leman-go-relational","title":"Weisfeiler and Leman Go Relational","date":"2022-11-30","arxiv_id":"2211.17113","repositories_listed":1,"syntology":null},{"url":"/paper/which-shortcut-solution-do-question-answering","slug":"which-shortcut-solution-do-question-answering","title":"Which Shortcut Solution Do Question Answering Models Prefer to Learn?","date":"2022-11-29","arxiv_id":"2211.16220","repositories_listed":1,"syntology":null},{"url":"/paper/improving-low-resource-question-answering","slug":"improving-low-resource-question-answering","title":"Combining Data Generation and Active Learning for Low-Resource Question Answering","date":"2022-11-27","arxiv_id":"2211.14880","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-what-you-miss-vision-language-pre","slug":"seeing-what-you-miss-vision-language-pre","title":"Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning","date":"2022-11-24","arxiv_id":"2211.13437","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-contrastive-learning-for-robust","slug":"cross-modal-contrastive-learning-for-robust","title":"Cross-Modal Contrastive Learning for Robust Reasoning in VQA","date":"2022-11-21","arxiv_id":"2211.11190","repositories_listed":1,"syntology":null},{"url":"/paper/visual-programming-compositional-visual","slug":"visual-programming-compositional-visual","title":"Visual Programming: Compositional visual reasoning without training","date":"2022-11-18","arxiv_id":"2211.11559","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/visual-programming-compositional-visual#ran","syntology_url":"https://syntology.ai/paper/2211.11559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11559"}},"official":null}},{"url":"/paper/i-can-t-believe-there-s-no-images-learning","slug":"i-can-t-believe-there-s-no-images-learning","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","date":"2022-11-17","arxiv_id":"2211.09778","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/i-can-t-believe-there-s-no-images-learning#ran","syntology_url":"https://syntology.ai/paper/2211.09778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09778"}},"official":{"repos":["allenai/close"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/open-domain-conversational-question-answering","slug":"open-domain-conversational-question-answering","title":"Open-Domain Conversational Question Answering with Historical Answers","date":"2022-11-17","arxiv_id":"2211.09401","repositories_listed":1,"syntology":null},{"url":"/paper/visual-commonsense-aware-representation","slug":"visual-commonsense-aware-representation","title":"Visual Commonsense-aware Representation Network for Video Captioning","date":"2022-11-17","arxiv_id":"2211.09469","repositories_listed":1,"syntology":null},{"url":"/paper/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","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/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}},"official":{"repos":["paperswithcode/galai"],"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"]}}}],"record_sha256":"d8b8b76df06f8096c8ae0ee13a837ee420bf5b6dd3721f32337d7165f3b3d98c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}