{"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/28","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":28,"pages_in_order":109,"rows_per_page":100,"rows":[2701,2800],"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/27","next":"/task/question-answering/papers/29","papers":[{"url":"/paper/retromae-v2-duplex-masked-auto-encoder-for","slug":"retromae-v2-duplex-masked-auto-encoder-for","title":"RetroMAE v2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models","date":"2022-11-16","arxiv_id":"2211.08769","repositories_listed":1,"syntology":null},{"url":"/paper/unified-question-answering-in-slovene","slug":"unified-question-answering-in-slovene","title":"Unified Question Answering in Slovene","date":"2022-11-16","arxiv_id":"2211.09159","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparative-study-of-question-answering","slug":"a-comparative-study-of-question-answering","title":"A Comparative Study of Question Answering over Knowledge Bases","date":"2022-11-15","arxiv_id":"2211.08170","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-struggle-to-learn-long","slug":"large-language-models-struggle-to-learn-long","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","date":"2022-11-15","arxiv_id":"2211.08411","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-struggle-to-learn-long#ran","syntology_url":"https://syntology.ai/paper/2211.08411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.08411"}},"official":{"repos":["nkandpa2/long_tail_knowledge"],"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/mapqa-a-dataset-for-question-answering-on","slug":"mapqa-a-dataset-for-question-answering-on","title":"MapQA: A Dataset for Question Answering on Choropleth Maps","date":"2022-11-15","arxiv_id":"2211.08545","repositories_listed":1,"syntology":null},{"url":"/paper/promptcap-prompt-guided-task-aware-image","slug":"promptcap-prompt-guided-task-aware-image","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","date":"2022-11-15","arxiv_id":"2211.09699","repositories_listed":1,"syntology":null},{"url":"/paper/qameleon-multilingual-qa-with-only-5-examples","slug":"qameleon-multilingual-qa-with-only-5-examples","title":"QAmeleon: Multilingual QA with Only 5 Examples","date":"2022-11-15","arxiv_id":"2211.08264","repositories_listed":1,"syntology":null},{"url":"/paper/visually-grounded-vqa-by-lattice-based","slug":"visually-grounded-vqa-by-lattice-based","title":"Visually Grounded VQA by Lattice-based Retrieval","date":"2022-11-15","arxiv_id":"2211.08086","repositories_listed":1,"syntology":null},{"url":"/paper/multi-vqg-generating-engaging-questions-for","slug":"multi-vqg-generating-engaging-questions-for","title":"Multi-VQG: Generating Engaging Questions for Multiple Images","date":"2022-11-14","arxiv_id":"2211.07441","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-augmented-generative-question","slug":"retrieval-augmented-generative-question","title":"Retrieval-Augmented Generative Question Answering for Event Argument Extraction","date":"2022-11-14","arxiv_id":"2211.07067","repositories_listed":1,"syntology":null},{"url":"/paper/mining-mathematical-documents-for-question","slug":"mining-mathematical-documents-for-question","title":"Mining Mathematical Documents for Question Answering via Unsupervised Formula Labeling","date":"2022-11-12","arxiv_id":"2211.06664","repositories_listed":1,"syntology":null},{"url":"/paper/disentqa-disentangling-parametric-and","slug":"disentqa-disentangling-parametric-and","title":"DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering","date":"2022-11-10","arxiv_id":"2211.05655","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/disentqa-disentangling-parametric-and#ran","syntology_url":"https://syntology.ai/paper/2211.05655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05655"}},"official":{"repos":["ellaneeman/disent_qa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-named-entity-linking-a-new-dataset-and","slug":"visual-named-entity-linking-a-new-dataset-and","title":"Visual Named Entity Linking: A New Dataset and A Baseline","date":"2022-11-09","arxiv_id":"2211.04872","repositories_listed":1,"syntology":null},{"url":"/paper/cov19ir-covid-19-domain-literature","slug":"cov19ir-covid-19-domain-literature","title":"COV19IR : COVID-19 Domain Literature Information Retrieval","date":"2022-11-08","arxiv_id":"2211.04013","repositories_listed":1,"syntology":null},{"url":"/paper/cripp-vqa-counterfactual-reasoning-about","slug":"cripp-vqa-counterfactual-reasoning-about","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","date":"2022-11-07","arxiv_id":"2211.03779","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cripp-vqa-counterfactual-reasoning-about#ran","syntology_url":"https://syntology.ai/paper/2211.03779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03779"}},"official":{"repos":["maitreyapatel/cripp-vqa"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/kglm-integrating-knowledge-graph-structure-in","slug":"kglm-integrating-knowledge-graph-structure-in","title":"KGLM: Integrating Knowledge Graph Structure in Language Models for Link Prediction","date":"2022-11-04","arxiv_id":"2211.02744","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/kglm-integrating-knowledge-graph-structure-in#ran","syntology_url":"https://syntology.ai/paper/2211.02744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.02744"}},"official":{"repos":["ibpa/kglm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/crosslingual-generalization-through-multitask","slug":"crosslingual-generalization-through-multitask","title":"Crosslingual Generalization through Multitask Finetuning","date":"2022-11-03","arxiv_id":"2211.01786","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/crosslingual-generalization-through-multitask#ran","syntology_url":"https://syntology.ai/paper/2211.01786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01786"}},"official":{"repos":["bigscience-workshop/xmtf"],"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/rquge-reference-free-metric-for-evaluating","slug":"rquge-reference-free-metric-for-evaluating","title":"RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question","date":"2022-11-02","arxiv_id":"2211.01482","repositories_listed":1,"syntology":null},{"url":"/paper/t5lephone-bridging-speech-and-text-self","slug":"t5lephone-bridging-speech-and-text-self","title":"T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5","date":"2022-11-01","arxiv_id":"2211.00586","repositories_listed":1,"syntology":null},{"url":"/paper/lila-a-unified-benchmark-for-mathematical","slug":"lila-a-unified-benchmark-for-mathematical","title":"Lila: A Unified Benchmark for Mathematical Reasoning","date":"2022-10-31","arxiv_id":"2210.17517","repositories_listed":1,"syntology":null},{"url":"/paper/an-efficient-memory-augmented-transformer-for","slug":"an-efficient-memory-augmented-transformer-for","title":"An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks","date":"2022-10-30","arxiv_id":"2210.16773","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-with-synthetic-corpora-for","slug":"transfer-learning-with-synthetic-corpora-for","title":"Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning","date":"2022-10-30","arxiv_id":"2210.16952","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/transfer-learning-with-synthetic-corpora-for#ran","syntology_url":"https://syntology.ai/paper/2210.16952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16952"}},"official":{"repos":["hlr/spartun"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/two-is-better-than-many-binary-classification","slug":"two-is-better-than-many-binary-classification","title":"Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering","date":"2022-10-29","arxiv_id":"2210.16495","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/two-is-better-than-many-binary-classification#ran","syntology_url":"https://syntology.ai/paper/2210.16495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16495"}},"official":{"repos":["declare-lab/team"],"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/fast-distilbert-on-cpus","slug":"fast-distilbert-on-cpus","title":"Fast DistilBERT on CPUs","date":"2022-10-27","arxiv_id":"2211.07715","repositories_listed":1,"syntology":null},{"url":"/paper/morphte-injecting-morphology-in-tensorized","slug":"morphte-injecting-morphology-in-tensorized","title":"MorphTE: Injecting Morphology in Tensorized Embeddings","date":"2022-10-27","arxiv_id":"2210.15379","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/morphte-injecting-morphology-in-tensorized#ran","syntology_url":"https://syntology.ai/paper/2210.15379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15379"}},"official":{"repos":["bigganbing/Fairseq_MorphTE"],"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/tasa-deceiving-question-answering-models-by","slug":"tasa-deceiving-question-answering-models-by","title":"TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack","date":"2022-10-27","arxiv_id":"2210.15221","repositories_listed":1,"syntology":null},{"url":"/paper/compressing-and-debiasing-vision-language-pre","slug":"compressing-and-debiasing-vision-language-pre","title":"Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering","date":"2022-10-26","arxiv_id":"2210.14558","repositories_listed":1,"syntology":null},{"url":"/paper/cs1qa-a-dataset-for-assisting-code-based-1","slug":"cs1qa-a-dataset-for-assisting-code-based-1","title":"CS1QA: A Dataset for Assisting Code-based Question Answering in an Introductory Programming Course","date":"2022-10-26","arxiv_id":"2210.14494","repositories_listed":1,"syntology":null},{"url":"/paper/dyrex-dynamic-query-representation-for","slug":"dyrex-dynamic-query-representation-for","title":"DyREx: Dynamic Query Representation for Extractive Question Answering","date":"2022-10-26","arxiv_id":"2210.15048","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dyrex-dynamic-query-representation-for#ran","syntology_url":"https://syntology.ai/paper/2210.15048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15048"}},"official":{"repos":["urchade/dyrex"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/what-s-different-between-visual-question","slug":"what-s-different-between-visual-question","title":"What's Different between Visual Question Answering for Machine \"Understanding\" Versus for Accessibility?","date":"2022-10-26","arxiv_id":"2210.14966","repositories_listed":1,"syntology":null},{"url":"/paper/romqa-a-benchmark-for-robust-multi-evidence","slug":"romqa-a-benchmark-for-robust-multi-evidence","title":"RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering","date":"2022-10-25","arxiv_id":"2210.14353","repositories_listed":1,"syntology":null},{"url":"/paper/event-centric-question-answering-via","slug":"event-centric-question-answering-via","title":"Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation","date":"2022-10-24","arxiv_id":"2210.12902","repositories_listed":1,"syntology":null},{"url":"/paper/rearev-adaptive-reasoning-for-question","slug":"rearev-adaptive-reasoning-for-question","title":"ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs","date":"2022-10-24","arxiv_id":"2210.13650","repositories_listed":1,"syntology":null},{"url":"/paper/vlc-bert-visual-question-answering-with","slug":"vlc-bert-visual-question-answering-with","title":"VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge","date":"2022-10-24","arxiv_id":"2210.13626","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/vlc-bert-visual-question-answering-with#ran","syntology_url":"https://syntology.ai/paper/2210.13626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13626"}},"official":{"repos":["aditya10/vlc-bert"],"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/cross-document-event-coreference-search-task","slug":"cross-document-event-coreference-search-task","title":"Cross-document Event Coreference Search: Task, Dataset and Modeling","date":"2022-10-23","arxiv_id":"2210.12654","repositories_listed":1,"syntology":null},{"url":"/paper/rsvg-exploring-data-and-models-for-visual","slug":"rsvg-exploring-data-and-models-for-visual","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","date":"2022-10-23","arxiv_id":"2210.12634","repositories_listed":1,"syntology":null},{"url":"/paper/tape-assessing-few-shot-russian-language","slug":"tape-assessing-few-shot-russian-language","title":"TAPE: Assessing Few-shot Russian Language Understanding","date":"2022-10-23","arxiv_id":"2210.12813","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-large-language-models-for-multiple","slug":"leveraging-large-language-models-for-multiple","title":"Leveraging Large Language Models for Multiple Choice Question Answering","date":"2022-10-22","arxiv_id":"2210.12353","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/leveraging-large-language-models-for-multiple#ran","syntology_url":"https://syntology.ai/paper/2210.12353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12353"}},"official":{"repos":["byu-pccl/leveraging-llms-for-mcqa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reastap-injecting-table-reasoning-skills","slug":"reastap-injecting-table-reasoning-skills","title":"ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples","date":"2022-10-22","arxiv_id":"2210.12374","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reastap-injecting-table-reasoning-skills#ran","syntology_url":"https://syntology.ai/paper/2210.12374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12374"}},"official":{"repos":["yale-lily/reastap"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/varifocal-question-generation-for-fact","slug":"varifocal-question-generation-for-fact","title":"Varifocal Question Generation for Fact-checking","date":"2022-10-22","arxiv_id":"2210.12400","repositories_listed":1,"syntology":null},{"url":"/paper/efficiently-tuned-parameters-are-task","slug":"efficiently-tuned-parameters-are-task","title":"Efficiently Tuned Parameters are Task Embeddings","date":"2022-10-21","arxiv_id":"2210.11705","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/efficiently-tuned-parameters-are-task#ran","syntology_url":"https://syntology.ai/paper/2210.11705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11705"}},"official":{"repos":["jetrunner/tupate"],"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/graphnet-graph-neural-networks-for-neutrino","slug":"graphnet-graph-neural-networks-for-neutrino","title":"GraphNeT: Graph neural networks for neutrino telescope event reconstruction","date":"2022-10-21","arxiv_id":"2210.12194","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/graphnet-graph-neural-networks-for-neutrino#ran","syntology_url":"https://syntology.ai/paper/2210.12194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12194"}},"official":{"repos":["graphnet-team/graphnet"],"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/informask-unsupervised-informative-masking","slug":"informask-unsupervised-informative-masking","title":"InforMask: Unsupervised Informative Masking for Language Model Pretraining","date":"2022-10-21","arxiv_id":"2210.11771","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/informask-unsupervised-informative-masking#ran","syntology_url":"https://syntology.ai/paper/2210.11771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11771"}},"official":{"repos":["nafissadeq/informask"],"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/posescript-3d-human-poses-from-natural","slug":"posescript-3d-human-poses-from-natural","title":"PoseScript: Linking 3D Human Poses and Natural Language","date":"2022-10-21","arxiv_id":"2210.11795","repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-relevance-feedback-for","slug":"incorporating-relevance-feedback-for","title":"Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking","date":"2022-10-19","arxiv_id":"2210.10695","repositories_listed":1,"syntology":null},{"url":"/paper/muger-2-multi-granularity-evidence-retrieval","slug":"muger-2-multi-granularity-evidence-retrieval","title":"MuGER$^2$: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering","date":"2022-10-19","arxiv_id":"2210.10350","repositories_listed":1,"syntology":null},{"url":"/paper/perception-test-a-diagnostic-benchmark-for","slug":"perception-test-a-diagnostic-benchmark-for","title":"Perception Test: A Diagnostic Benchmark for Multimodal Models","date":"2022-10-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/qa-domain-adaptation-using-hidden-space","slug":"qa-domain-adaptation-using-hidden-space","title":"QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation","date":"2022-10-19","arxiv_id":"2210.10861","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":2,"n_ran_checked":8,"n_instrument":4,"n_unverified":4,"n_honours":5,"n_violates":1,"n_no_contract":2,"n_pointer_only":16,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 5 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/qa-domain-adaptation-using-hidden-space#ran","syntology_url":"https://syntology.ai/paper/2210.10861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10861"}},"official":{"repos":["yueeeeeeee/self-supervised-qa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/elastic-numerical-reasoning-with-adaptive","slug":"elastic-numerical-reasoning-with-adaptive","title":"ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler","date":"2022-10-18","arxiv_id":"2210.10105","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"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 1 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/elastic-numerical-reasoning-with-adaptive#ran","syntology_url":"https://syntology.ai/paper/2210.10105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10105"}},"official":{"repos":["neurasearch/neurips-2022-submission-3358"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cave-correcting-attribute-values-in-e","slug":"cave-correcting-attribute-values-in-e","title":"CAVE: Correcting Attribute Values in E-commerce Profiles","date":"2022-10-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pacific-towards-proactive-conversational","slug":"pacific-towards-proactive-conversational","title":"PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance","date":"2022-10-17","arxiv_id":"2210.08817","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/pacific-towards-proactive-conversational#ran","syntology_url":"https://syntology.ai/paper/2210.08817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08817"}},"official":{"repos":["dengyang17/pacific"],"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/vision-language-pre-training-basics-recent","slug":"vision-language-pre-training-basics-recent","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","date":"2022-10-17","arxiv_id":"2210.09263","repositories_listed":1,"syntology":null},{"url":"/paper/unirpg-unified-discrete-reasoning-over-table","slug":"unirpg-unified-discrete-reasoning-over-table","title":"UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation","date":"2022-10-15","arxiv_id":"2210.08249","repositories_listed":1,"syntology":null},{"url":"/paper/video-in-10-bits-few-bit-videoqa-for","slug":"video-in-10-bits-few-bit-videoqa-for","title":"Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy","date":"2022-10-15","arxiv_id":"2210.08391","repositories_listed":1,"syntology":null},{"url":"/paper/conentail-an-entailment-based-framework-for","slug":"conentail-an-entailment-based-framework-for","title":"ConEntail: An Entailment-based Framework for Universal Zero and Few Shot Classification with Supervised Contrastive Pretraining","date":"2022-10-14","arxiv_id":"2210.07587","repositories_listed":1,"syntology":null},{"url":"/paper/john-is-50-years-old-can-his-son-be-65","slug":"john-is-50-years-old-can-his-son-be-65","title":"\"John is 50 years old, can his son be 65?\" Evaluating NLP Models' Understanding of Feasibility","date":"2022-10-14","arxiv_id":"2210.07471","repositories_listed":1,"syntology":null},{"url":"/paper/mico-a-multi-alternative-contrastive-learning","slug":"mico-a-multi-alternative-contrastive-learning","title":"MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation","date":"2022-10-14","arxiv_id":"2210.07570","repositories_listed":1,"syntology":null},{"url":"/paper/sqa3d-situated-question-answering-in-3d","slug":"sqa3d-situated-question-answering-in-3d","title":"SQA3D: Situated Question Answering in 3D Scenes","date":"2022-10-14","arxiv_id":"2210.07474","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":6,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sqa3d-situated-question-answering-in-3d#ran","syntology_url":"https://syntology.ai/paper/2210.07474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07474"}},"official":{"repos":["SilongYong/SQA3D"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-long-tail-generalization-with","slug":"benchmarking-long-tail-generalization-with","title":"Benchmarking Long-tail Generalization with Likelihood Splits","date":"2022-10-13","arxiv_id":"2210.06799","repositories_listed":1,"syntology":null},{"url":"/paper/closed-book-question-generation-via","slug":"closed-book-question-generation-via","title":"Closed-book Question Generation via Contrastive Learning","date":"2022-10-13","arxiv_id":"2210.06781","repositories_listed":1,"syntology":null},{"url":"/paper/mapl-parameter-efficient-adaptation-of","slug":"mapl-parameter-efficient-adaptation-of","title":"MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting","date":"2022-10-13","arxiv_id":"2210.07179","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":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) · 0 unverified","sample_list":"/paper/mapl-parameter-efficient-adaptation-of#ran","syntology_url":"https://syntology.ai/paper/2210.07179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07179"}},"official":{"repos":["mair-lab/mapl"],"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/shortcomings-of-question-answering-based","slug":"shortcomings-of-question-answering-based","title":"Shortcomings of Question Answering Based Factuality Frameworks for Error Localization","date":"2022-10-13","arxiv_id":"2210.06748","repositories_listed":1,"syntology":null},{"url":"/paper/sodapop-open-ended-discovery-of-social-biases","slug":"sodapop-open-ended-discovery-of-social-biases","title":"SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models","date":"2022-10-13","arxiv_id":"2210.07269","repositories_listed":1,"syntology":null},{"url":"/paper/towards-end-to-end-open-conversational","slug":"towards-end-to-end-open-conversational","title":"Towards End-to-End Open Conversational Machine Reading","date":"2022-10-13","arxiv_id":"2210.07113","repositories_listed":1,"syntology":null},{"url":"/paper/discourse-analysis-via-questions-and-answers","slug":"discourse-analysis-via-questions-and-answers","title":"Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion","date":"2022-10-12","arxiv_id":"2210.05905","repositories_listed":1,"syntology":null},{"url":"/paper/long-form-video-language-pre-training-with","slug":"long-form-video-language-pre-training-with","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","date":"2022-10-12","arxiv_id":"2210.06031","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-form-video-language-pre-training-with#ran","syntology_url":"https://syntology.ai/paper/2210.06031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06031"}},"official":{"repos":["microsoft/xpretrain"],"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/opencqa-open-ended-question-answering-with","slug":"opencqa-open-ended-question-answering-with","title":"OpenCQA: Open-ended Question Answering with Charts","date":"2022-10-12","arxiv_id":"2210.06628","repositories_listed":1,"syntology":null},{"url":"/paper/probing-commonsense-knowledge-in-pre-trained","slug":"probing-commonsense-knowledge-in-pre-trained","title":"Probing Commonsense Knowledge in Pre-trained Language Models with Sense-level Precision and Expanded Vocabulary","date":"2022-10-12","arxiv_id":"2210.06376","repositories_listed":1,"syntology":null},{"url":"/paper/slotformer-unsupervised-visual-dynamics","slug":"slotformer-unsupervised-visual-dynamics","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","date":"2022-10-12","arxiv_id":"2210.05861","repositories_listed":1,"syntology":null},{"url":"/paper/task-compass-scaling-multi-task-pre-training","slug":"task-compass-scaling-multi-task-pre-training","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","date":"2022-10-12","arxiv_id":"2210.06277","repositories_listed":1,"syntology":null},{"url":"/paper/capturing-global-structural-information-in","slug":"capturing-global-structural-information-in","title":"Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network","date":"2022-10-11","arxiv_id":"2210.05499","repositories_listed":1,"syntology":null},{"url":"/paper/how-well-do-multi-hop-reading-comprehension-1","slug":"how-well-do-multi-hop-reading-comprehension-1","title":"How Well Do Multi-hop Reading Comprehension Models Understand Date Information?","date":"2022-10-11","arxiv_id":"2210.05208","repositories_listed":1,"syntology":null},{"url":"/paper/map-modality-agnostic-uncertainty-aware","slug":"map-modality-agnostic-uncertainty-aware","title":"MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model","date":"2022-10-11","arxiv_id":"2210.05335","repositories_listed":1,"syntology":null},{"url":"/paper/mixed-modality-representation-learning-and","slug":"mixed-modality-representation-learning-and","title":"Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA","date":"2022-10-11","arxiv_id":"2210.05197","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mixed-modality-representation-learning-and#ran","syntology_url":"https://syntology.ai/paper/2210.05197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05197"}},"official":{"repos":["jun-jie-huang/otter"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/task-aware-specialization-for-efficient-and","slug":"task-aware-specialization-for-efficient-and","title":"Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering","date":"2022-10-11","arxiv_id":"2210.05156","repositories_listed":1,"syntology":null},{"url":"/paper/language-prior-is-not-the-only-shortcut-a","slug":"language-prior-is-not-the-only-shortcut-a","title":"Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA","date":"2022-10-10","arxiv_id":"2210.04692","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-visual-question-answering","slug":"towards-robust-visual-question-answering","title":"Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning","date":"2022-10-10","arxiv_id":"2210.04563","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-robust-visual-question-answering#ran","syntology_url":"https://syntology.ai/paper/2210.04563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.04563"}},"official":{"repos":["phoebussi/mmbs"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/contrastive-representation-learning-for-1","slug":"contrastive-representation-learning-for-1","title":"Contrastive Representation Learning for Conversational Question Answering over Knowledge Graphs","date":"2022-10-09","arxiv_id":"2210.04373","repositories_listed":1,"syntology":null},{"url":"/paper/egotaskqa-understanding-human-tasks-in","slug":"egotaskqa-understanding-human-tasks-in","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","date":"2022-10-08","arxiv_id":"2210.03929","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/egotaskqa-understanding-human-tasks-in#ran","syntology_url":"https://syntology.ai/paper/2210.03929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03929"}},"official":{"repos":["Buzz-Beater/EgoTaskQA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-language-models-for-paragraph","slug":"generative-language-models-for-paragraph","title":"Generative Language Models for Paragraph-Level Question Generation","date":"2022-10-08","arxiv_id":"2210.03992","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generative-language-models-for-paragraph#ran","syntology_url":"https://syntology.ai/paper/2210.03992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03992"}},"official":{"repos":["asahi417/lm-question-generation"],"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/learning-fine-grained-visual-understanding","slug":"learning-fine-grained-visual-understanding","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","date":"2022-10-08","arxiv_id":"2210.03941","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-encoder-decoder-framework-with","slug":"a-unified-encoder-decoder-framework-with","title":"A Unified Encoder-Decoder Framework with Entity Memory","date":"2022-10-07","arxiv_id":"2210.03273","repositories_listed":1,"syntology":null},{"url":"/paper/calibrating-factual-knowledge-in-pretrained","slug":"calibrating-factual-knowledge-in-pretrained","title":"Calibrating Factual Knowledge in Pretrained Language Models","date":"2022-10-07","arxiv_id":"2210.03329","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/calibrating-factual-knowledge-in-pretrained#ran","syntology_url":"https://syntology.ai/paper/2210.03329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03329"}},"official":{"repos":["dqxiu/calinet"],"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/convfinqa-exploring-the-chain-of-numerical","slug":"convfinqa-exploring-the-chain-of-numerical","title":"ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering","date":"2022-10-07","arxiv_id":"2210.03849","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/convfinqa-exploring-the-chain-of-numerical#ran","syntology_url":"https://syntology.ai/paper/2210.03849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03849"}},"official":{"repos":["czyssrs/convfinqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/measuring-and-narrowing-the-compositionality","slug":"measuring-and-narrowing-the-compositionality","title":"Measuring and Narrowing the Compositionality Gap in Language Models","date":"2022-10-07","arxiv_id":"2210.03350","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-augmented-visual-question-answering","slug":"retrieval-augmented-visual-question-answering","title":"Retrieval Augmented Visual Question Answering with Outside Knowledge","date":"2022-10-07","arxiv_id":"2210.03809","repositories_listed":1,"syntology":null},{"url":"/paper/grape-knowledge-graph-enhanced-passage-reader","slug":"grape-knowledge-graph-enhanced-passage-reader","title":"Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering","date":"2022-10-06","arxiv_id":"2210.02933","repositories_listed":1,"syntology":null},{"url":"/paper/guess-the-instruction-making-language-models","slug":"guess-the-instruction-making-language-models","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","date":"2022-10-06","arxiv_id":"2210.02969","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-domain-adaptation-of-retrieval","slug":"improving-the-domain-adaptation-of-retrieval","title":"Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering","date":"2022-10-06","arxiv_id":"2210.02627","repositories_listed":1,"syntology":null},{"url":"/paper/just-cloze-a-fast-and-simple-method-for","slug":"just-cloze-a-fast-and-simple-method-for","title":"Just ClozE! A Novel Framework for Evaluating the Factual Consistency Faster in Abstractive Summarization","date":"2022-10-06","arxiv_id":"2210.02804","repositories_listed":1,"syntology":null},{"url":"/paper/rainier-reinforced-knowledge-introspector-for","slug":"rainier-reinforced-knowledge-introspector-for","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","date":"2022-10-06","arxiv_id":"2210.03078","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":6,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/rainier-reinforced-knowledge-introspector-for#ran","syntology_url":"https://syntology.ai/paper/2210.03078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03078"}},"official":{"repos":["liujch1998/rainier"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/emotion-twenty-questions-dialog-system-for","slug":"emotion-twenty-questions-dialog-system-for","title":"Emotion Twenty Questions Dialog System for Lexical Emotional Intelligence","date":"2022-10-05","arxiv_id":"2210.02400","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-are-pretty-good-zero","slug":"large-language-models-are-pretty-good-zero","title":"Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors","date":"2022-10-05","arxiv_id":"2210.02506","repositories_listed":1,"syntology":null},{"url":"/paper/mintaka-a-complex-natural-and-multilingual","slug":"mintaka-a-complex-natural-and-multilingual","title":"Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering","date":"2022-10-04","arxiv_id":"2210.01613","repositories_listed":1,"syntology":null},{"url":"/paper/recitation-augmented-language-models","slug":"recitation-augmented-language-models","title":"Recitation-Augmented Language Models","date":"2022-10-04","arxiv_id":"2210.01296","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/recitation-augmented-language-models#ran","syntology_url":"https://syntology.ai/paper/2210.01296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01296"}},"official":{"repos":["edward-sun/recite"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-improving-faithfulness-in-abstractive","slug":"towards-improving-faithfulness-in-abstractive","title":"Towards Improving Faithfulness in Abstractive Summarization","date":"2022-10-04","arxiv_id":"2210.01877","repositories_listed":1,"syntology":null},{"url":"/paper/when-to-make-exceptions-exploring-language","slug":"when-to-make-exceptions-exploring-language","title":"When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment","date":"2022-10-04","arxiv_id":"2210.01478","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/when-to-make-exceptions-exploring-language#ran","syntology_url":"https://syntology.ai/paper/2210.01478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01478"}},"official":{"repos":["feradauto/moralcot"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/extending-compositional-attention-networks","slug":"extending-compositional-attention-networks","title":"Extending Compositional Attention Networks for Social Reasoning in Videos","date":"2022-10-03","arxiv_id":"2210.01191","repositories_listed":1,"syntology":null},{"url":"/paper/a-dual-attention-learning-network-with-word","slug":"a-dual-attention-learning-network-with-word","title":"A Dual-Attention Learning Network with Word and Sentence Embedding for Medical Visual Question Answering","date":"2022-10-01","arxiv_id":"2210.00220","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-multilingual-embeddings-for-improved","slug":"aligning-multilingual-embeddings-for-improved","title":"Aligning Multilingual Embeddings for Improved Code-switched Natural Language Understanding","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"record_sha256":"ad80209e70bab5d20b4bf48ad2629a0c5ebcaf40a171c102238f608f1ec37141","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}