{"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/reading-comprehension/papers/3","list_of":"/task/reading-comprehension","task":"Reading Comprehension","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":3,"pages_in_order":18,"rows_per_page":100,"rows":[201,300],"of":1760,"counts":{"archive_papers_tagged":1760,"with_a_code_link":634,"where_syntology_ran_a_sample":139,"not_listed_spam_title":0,"listed":1760,"listed_where_code_ran":139,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":120,"every_run_a_failure_of_syntologys_instrument":19,"listed_with_a_run_with_no_instrument_failure":120,"listed_every_run_a_failure_of_syntologys_instrument":19,"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/reading-comprehension","prev":"/task/reading-comprehension/papers/2","next":"/task/reading-comprehension/papers/4","papers":[{"url":"/paper/gym-at-quran-qa-2023-shared-task-multi-task","slug":"gym-at-quran-qa-2023-shared-task-multi-task","title":"GYM at Qur’an QA 2023 Shared Task: Multi-Task Transfer Learning for Quranic Passage Retrieval and Question Answering with Large Language Models","date":"2023-12-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gpt4point-a-unified-framework-for-point","slug":"gpt4point-a-unified-framework-for-point","title":"GPT4Point: A Unified Framework for Point-Language Understanding and Generation","date":"2023-12-05","arxiv_id":"2312.02980","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gpt4point-a-unified-framework-for-point#ran","syntology_url":"https://syntology.ai/paper/2312.02980","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02980"}},"official":null}},{"url":"/paper/let-the-llms-talk-simulating-human-to-human","slug":"let-the-llms-talk-simulating-human-to-human","title":"Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions","date":"2023-12-05","arxiv_id":"2312.02913","repositories_listed":1,"syntology":null},{"url":"/paper/eeg-connectivity-analysis-using-denoising","slug":"eeg-connectivity-analysis-using-denoising","title":"EEG Connectivity Analysis Using Denoising Autoencoders for the Detection of Dyslexia","date":"2023-11-23","arxiv_id":"2311.13876","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-text-retrieval-with","slug":"towards-robust-text-retrieval-with","title":"Towards Robust Text Retrieval with Progressive Learning","date":"2023-11-20","arxiv_id":"2311.11691","repositories_listed":1,"syntology":null},{"url":"/paper/token-level-adaptation-of-lora-adapters-for","slug":"token-level-adaptation-of-lora-adapters-for","title":"Token-Level Adaptation of LoRA Adapters for Downstream Task Generalization","date":"2023-11-17","arxiv_id":"2311.10847","repositories_listed":1,"syntology":null},{"url":"/paper/debate-helps-supervise-unreliable-experts","slug":"debate-helps-supervise-unreliable-experts","title":"Debate Helps Supervise Unreliable Experts","date":"2023-11-15","arxiv_id":"2311.08702","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/debate-helps-supervise-unreliable-experts#ran","syntology_url":"https://syntology.ai/paper/2311.08702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08702"}},"official":{"repos":["julianmichael/debate"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mirror-a-universal-framework-for-various","slug":"mirror-a-universal-framework-for-various","title":"Mirror: A Universal Framework for Various Information Extraction Tasks","date":"2023-11-09","arxiv_id":"2311.05419","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/mirror-a-universal-framework-for-various#ran","syntology_url":"https://syntology.ai/paper/2311.05419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05419"}},"official":{"repos":["Spico197/Mirror"],"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/creoleval-multilingual-multitask-benchmarks","slug":"creoleval-multilingual-multitask-benchmarks","title":"CreoleVal: Multilingual Multitask Benchmarks for Creoles","date":"2023-10-30","arxiv_id":"2310.19567","repositories_listed":1,"syntology":null},{"url":"/paper/mprompt-exploring-multi-level-prompt-tuning","slug":"mprompt-exploring-multi-level-prompt-tuning","title":"MPrompt: Exploring Multi-level Prompt Tuning for Machine Reading Comprehension","date":"2023-10-27","arxiv_id":"2310.18167","repositories_listed":1,"syntology":null},{"url":"/paper/guiding-llm-to-fool-itself-automatically","slug":"guiding-llm-to-fool-itself-automatically","title":"Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers","date":"2023-10-24","arxiv_id":"2310.18360","repositories_listed":1,"syntology":null},{"url":"/paper/doctrack-a-visually-rich-document-dataset","slug":"doctrack-a-visually-rich-document-dataset","title":"DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine Reading","date":"2023-10-23","arxiv_id":"2310.14802","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-large-language-models-on","slug":"evaluating-large-language-models-on","title":"Evaluating Large Language Models on Controlled Generation Tasks","date":"2023-10-23","arxiv_id":"2310.14542","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-interactions-between-text-spans","slug":"explaining-interactions-between-text-spans","title":"Explaining Interactions Between Text Spans","date":"2023-10-20","arxiv_id":"2310.13506","repositories_listed":1,"syntology":null},{"url":"/paper/do-language-models-learn-about-legal-entity","slug":"do-language-models-learn-about-legal-entity","title":"Do Language Models Learn about Legal Entity Types during Pretraining?","date":"2023-10-19","arxiv_id":"2310.13092","repositories_listed":1,"syntology":null},{"url":"/paper/instructive-dialogue-summarization-with-query","slug":"instructive-dialogue-summarization-with-query","title":"Instructive Dialogue Summarization with Query Aggregations","date":"2023-10-17","arxiv_id":"2310.10981","repositories_listed":1,"syntology":null},{"url":"/paper/in-context-pretraining-language-modeling","slug":"in-context-pretraining-language-modeling","title":"In-context Pretraining: Language Modeling Beyond Document Boundaries","date":"2023-10-16","arxiv_id":"2310.10638","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/in-context-pretraining-language-modeling#ran","syntology_url":"https://syntology.ai/paper/2310.10638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10638"}},"official":{"repos":["swj0419/in-context-pretraining"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/instructretro-instruction-tuning-post","slug":"instructretro-instruction-tuning-post","title":"InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining","date":"2023-10-11","arxiv_id":"2310.07713","repositories_listed":1,"syntology":null},{"url":"/paper/compresso-structured-pruning-with","slug":"compresso-structured-pruning-with","title":"Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models","date":"2023-10-08","arxiv_id":"2310.05015","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":1,"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/compresso-structured-pruning-with#ran","syntology_url":"https://syntology.ai/paper/2310.05015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05015"}},"official":{"repos":["microsoft/moonlit"],"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/minigpt-5-interleaved-vision-and-language","slug":"minigpt-5-interleaved-vision-and-language","title":"MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens","date":"2023-10-03","arxiv_id":"2310.02239","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/minigpt-5-interleaved-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2310.02239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02239"}},"official":{"repos":["eric-ai-lab/minigpt-5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/named-entity-recognition-via-machine-reading","slug":"named-entity-recognition-via-machine-reading","title":"Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach","date":"2023-09-20","arxiv_id":"2309.11027","repositories_listed":1,"syntology":null},{"url":"/paper/estimating-contamination-via-perplexity","slug":"estimating-contamination-via-perplexity","title":"Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation","date":"2023-09-19","arxiv_id":"2309.10677","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-large-language-models-via-reading","slug":"adapting-large-language-models-via-reading","title":"Adapting Large Language Models to Domains via Reading Comprehension","date":"2023-09-18","arxiv_id":"2309.09530","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/adapting-large-language-models-via-reading#ran","syntology_url":"https://syntology.ai/paper/2309.09530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09530"}},"official":{"repos":["microsoft/lmops"],"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/echoprompt-instructing-the-model-to-rephrase","slug":"echoprompt-instructing-the-model-to-rephrase","title":"EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning","date":"2023-09-16","arxiv_id":"2309.10687","repositories_listed":1,"syntology":null},{"url":"/paper/hae-rae-bench-evaluation-of-korean-knowledge","slug":"hae-rae-bench-evaluation-of-korean-knowledge","title":"HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models","date":"2023-09-06","arxiv_id":"2309.02706","repositories_listed":1,"syntology":null},{"url":"/paper/generative-data-augmentation-using-llms","slug":"generative-data-augmentation-using-llms","title":"Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering","date":"2023-09-03","arxiv_id":"2309.06358","repositories_listed":1,"syntology":null},{"url":"/paper/chunk-align-select-a-simple-long-sequence","slug":"chunk-align-select-a-simple-long-sequence","title":"Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers","date":"2023-08-25","arxiv_id":"2308.13191","repositories_listed":1,"syntology":null},{"url":"/paper/yorc-yoruba-reading-comprehension-dataset","slug":"yorc-yoruba-reading-comprehension-dataset","title":"NaijaRC: A Multi-choice Reading Comprehension Dataset for Nigerian Languages","date":"2023-08-18","arxiv_id":"2308.09768","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-catastrophic-forgetting","slug":"an-empirical-study-of-catastrophic-forgetting","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","date":"2023-08-17","arxiv_id":"2308.08747","repositories_listed":1,"syntology":null},{"url":"/paper/demonstration-based-learning-for-few-shot","slug":"demonstration-based-learning-for-few-shot","title":"Demonstration-based learning for few-shot biomedical named entity recognition under machine reading comprehension","date":"2023-08-12","arxiv_id":"2308.06454","repositories_listed":1,"syntology":null},{"url":"/paper/ketm-a-knowledge-enhanced-text-matching","slug":"ketm-a-knowledge-enhanced-text-matching","title":"KETM:A Knowledge-Enhanced Text Matching method","date":"2023-08-11","arxiv_id":"2308.06235","repositories_listed":1,"syntology":null},{"url":"/paper/single-sentence-reader-a-novel-approach-for","slug":"single-sentence-reader-a-novel-approach-for","title":"Single-Sentence Reader: A Novel Approach for Addressing Answer Position Bias","date":"2023-08-08","arxiv_id":"2308.04566","repositories_listed":1,"syntology":null},{"url":"/paper/top-k-relevant-passage-retrieval-for","slug":"top-k-relevant-passage-retrieval-for","title":"Top K Relevant Passage Retrieval for Biomedical Question Answering","date":"2023-08-08","arxiv_id":"2308.04028","repositories_listed":1,"syntology":null},{"url":"/paper/recomif-reading-comprehension-based-multi","slug":"recomif-reading-comprehension-based-multi","title":"ReCoMIF: Reading comprehension based multi-source information fusion network for Chinese spoken language understanding","date":"2023-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-query-reformulation-for","slug":"zero-shot-query-reformulation-for","title":"ZeQR: Zero-shot Query Reformulation for Conversational Search","date":"2023-07-18","arxiv_id":"2307.09384","repositories_listed":1,"syntology":null},{"url":"/paper/korc-knowledge-oriented-reading-comprehension","slug":"korc-knowledge-oriented-reading-comprehension","title":"KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding","date":"2023-07-06","arxiv_id":"2307.03115","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/korc-knowledge-oriented-reading-comprehension#ran","syntology_url":"https://syntology.ai/paper/2307.03115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03115"}},"official":{"repos":["thu-keg/korc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multilingual-controllable-transformer-based","slug":"multilingual-controllable-transformer-based","title":"Multilingual Controllable Transformer-Based Lexical Simplification","date":"2023-07-05","arxiv_id":"2307.02120","repositories_listed":1,"syntology":null},{"url":"/paper/idol-indicator-oriented-logic-pre-training","slug":"idol-indicator-oriented-logic-pre-training","title":"IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning","date":"2023-06-27","arxiv_id":"2306.15273","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-level-event-detection-without","slug":"sentence-level-event-detection-without","title":"Sentence-level Event Detection without Triggers via Prompt Learning and Machine Reading Comprehension","date":"2023-06-25","arxiv_id":"2306.14176","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-end-to-end-learning-of","slug":"bidirectional-end-to-end-learning-of","title":"Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking","date":"2023-06-21","arxiv_id":"2306.12245","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-hierarchical-reasoning-chains-by-1","slug":"modeling-hierarchical-reasoning-chains-by-1","title":"Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension","date":"2023-06-21","arxiv_id":"2306.12069","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-gap-between-decision-and-logits","slug":"bridging-the-gap-between-decision-and-logits","title":"Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models","date":"2023-06-15","arxiv_id":"2306.08909","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/bridging-the-gap-between-decision-and-logits#ran","syntology_url":"https://syntology.ai/paper/2306.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08909"}},"official":{"repos":["thunlp-mt/dbkd-plm"],"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/improving-reading-comprehension-question","slug":"improving-reading-comprehension-question","title":"Improving Reading Comprehension Question Generation with Data Augmentation and Overgenerate-and-rank","date":"2023-06-15","arxiv_id":"2306.08847","repositories_listed":1,"syntology":null},{"url":"/paper/knowing-how-knowing-that-a-new-task-for","slug":"knowing-how-knowing-that-a-new-task-for","title":"Knowing-how & Knowing-that: A New Task for Machine Comprehension of User Manuals","date":"2023-06-07","arxiv_id":"2306.04187","repositories_listed":1,"syntology":null},{"url":"/paper/promptbench-towards-evaluating-the-robustness","slug":"promptbench-towards-evaluating-the-robustness","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","date":"2023-06-07","arxiv_id":"2306.04528","repositories_listed":1,"syntology":null},{"url":"/paper/logiqa-2-0-an-improved-dataset-for-logical","slug":"logiqa-2-0-an-improved-dataset-for-logical","title":"LogiQA 2.0—An Improved Dataset for Logical Reasoning in Natural Language Understanding","date":"2023-06-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/how-many-answers-should-i-give-an-empirical","slug":"how-many-answers-should-i-give-an-empirical","title":"How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension","date":"2023-06-01","arxiv_id":"2306.00435","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-are-not-abstract","slug":"large-language-models-are-not-abstract","title":"Large Language Models Are Not Strong Abstract Reasoners","date":"2023-05-31","arxiv_id":"2305.19555","repositories_listed":1,"syntology":null},{"url":"/paper/a-practical-toolkit-for-multilingual-question","slug":"a-practical-toolkit-for-multilingual-question","title":"A Practical Toolkit for Multilingual Question and Answer Generation","date":"2023-05-27","arxiv_id":"2305.17416","repositories_listed":1,"syntology":null},{"url":"/paper/a-causal-view-of-entity-bias-in-large","slug":"a-causal-view-of-entity-bias-in-large","title":"A Causal View of Entity Bias in (Large) Language Models","date":"2023-05-24","arxiv_id":"2305.14695","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-causal-view-of-entity-bias-in-large#ran","syntology_url":"https://syntology.ai/paper/2305.14695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14695"}},"official":{"repos":["luka-group/causal-view-of-entity-bias"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-contrast-consistency-of-open-domain","slug":"exploring-contrast-consistency-of-open-domain","title":"Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions","date":"2023-05-23","arxiv_id":"2305.14441","repositories_listed":1,"syntology":null},{"url":"/paper/mpmr-a-multilingual-pre-trained-machine","slug":"mpmr-a-multilingual-pre-trained-machine","title":"mPMR: A Multilingual Pre-trained Machine Reader at Scale","date":"2023-05-23","arxiv_id":"2305.13645","repositories_listed":1,"syntology":null},{"url":"/paper/narrative-xl-a-large-scale-dataset-for-long","slug":"narrative-xl-a-large-scale-dataset-for-long","title":"NarrativeXL: A Large-scale Dataset For Long-Term Memory Models","date":"2023-05-23","arxiv_id":"2305.13877","repositories_listed":1,"syntology":null},{"url":"/paper/wyweb-a-nlp-evaluation-benchmark-for","slug":"wyweb-a-nlp-evaluation-benchmark-for","title":"WYWEB: A NLP Evaluation Benchmark For Classical Chinese","date":"2023-05-23","arxiv_id":"2305.14150","repositories_listed":1,"syntology":null},{"url":"/paper/cross-functional-analysis-of-generalisation","slug":"cross-functional-analysis-of-generalisation","title":"Cross-functional Analysis of Generalisation in Behavioural Learning","date":"2023-05-22","arxiv_id":"2305.12951","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-with-logic-driven-data","slug":"contrastive-learning-with-logic-driven-data","title":"Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning","date":"2023-05-21","arxiv_id":"2305.12599","repositories_listed":1,"syntology":null},{"url":"/paper/vnhsge-vietnamese-high-school-graduation","slug":"vnhsge-vietnamese-high-school-graduation","title":"VNHSGE: VietNamese High School Graduation Examination Dataset for Large Language Models","date":"2023-05-20","arxiv_id":"2305.12199","repositories_listed":1,"syntology":null},{"url":"/paper/s-3-hqa-a-three-stage-approach-for-multi-hop","slug":"s-3-hqa-a-three-stage-approach-for-multi-hop","title":"S$^3$HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering","date":"2023-05-19","arxiv_id":"2305.11725","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/s-3-hqa-a-three-stage-approach-for-multi-hop#ran","syntology_url":"https://syntology.ai/paper/2305.11725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11725"}},"official":{"repos":["lfy79001/s3hqa"],"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/a-quantitative-study-of-nlp-approaches-to","slug":"a-quantitative-study-of-nlp-approaches-to","title":"A quantitative study of NLP approaches to question difficulty estimation","date":"2023-05-17","arxiv_id":"2305.10236","repositories_listed":1,"syntology":null},{"url":"/paper/coreference-aware-double-channel-attention","slug":"coreference-aware-double-channel-attention","title":"Coreference-aware Double-channel Attention Network for Multi-party Dialogue Reading Comprehension","date":"2023-05-15","arxiv_id":"2305.08348","repositories_listed":1,"syntology":null},{"url":"/paper/embrace-evaluation-and-modifications-for","slug":"embrace-evaluation-and-modifications-for","title":"EMBRACE: Evaluation and Modifications for Boosting RACE","date":"2023-05-15","arxiv_id":"2305.08433","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-loose-optimization-for-robust","slug":"adaptive-loose-optimization-for-robust","title":"Adaptive loose optimization for robust question answering","date":"2023-05-06","arxiv_id":"2305.03971","repositories_listed":1,"syntology":null},{"url":"/paper/a-large-cross-modal-video-retrieval-dataset","slug":"a-large-cross-modal-video-retrieval-dataset","title":"A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension","date":"2023-05-05","arxiv_id":"2305.03347","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":3,"phrase":"12 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-large-cross-modal-video-retrieval-dataset#ran","syntology_url":"https://syntology.ai/paper/2305.03347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.03347"}},"official":{"repos":["callsys/textvr"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-view-graph-representation-learning-for","slug":"multi-view-graph-representation-learning-for","title":"Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Question","date":"2023-05-05","arxiv_id":"2305.03458","repositories_listed":1,"syntology":null},{"url":"/paper/norquad-norwegian-question-answering-dataset","slug":"norquad-norwegian-question-answering-dataset","title":"NorQuAD: Norwegian Question Answering Dataset","date":"2023-05-03","arxiv_id":"2305.01957","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-logical-reasoning-ability-of","slug":"evaluating-the-logical-reasoning-ability-of","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","date":"2023-04-07","arxiv_id":"2304.03439","repositories_listed":1,"syntology":null},{"url":"/paper/minirbt-a-two-stage-distilled-small-chinese","slug":"minirbt-a-two-stage-distilled-small-chinese","title":"MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model","date":"2023-04-03","arxiv_id":"2304.00717","repositories_listed":1,"syntology":null},{"url":"/paper/a-multiple-choices-reading-comprehension","slug":"a-multiple-choices-reading-comprehension","title":"A Multiple Choices Reading Comprehension Corpus for Vietnamese Language Education","date":"2023-03-31","arxiv_id":"2303.18162","repositories_listed":1,"syntology":null},{"url":"/paper/context-faithful-prompting-for-large-language","slug":"context-faithful-prompting-for-large-language","title":"Context-faithful Prompting for Large Language Models","date":"2023-03-20","arxiv_id":"2303.11315","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/context-faithful-prompting-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2303.11315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11315"}},"official":{"repos":["wzhouad/context-faithful-llm"],"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/orca-a-few-shot-benchmark-for-chinese","slug":"orca-a-few-shot-benchmark-for-chinese","title":"Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehension","date":"2023-02-27","arxiv_id":"2302.13619","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-question-answering-over","slug":"cross-lingual-question-answering-over","title":"Cross-Lingual Question Answering over Knowledge Base as Reading Comprehension","date":"2023-02-26","arxiv_id":"2302.13241","repositories_listed":1,"syntology":null},{"url":"/paper/natural-response-generation-for-chinese","slug":"natural-response-generation-for-chinese","title":"Natural Response Generation for Chinese Reading Comprehension","date":"2023-02-17","arxiv_id":"2302.08817","repositories_listed":1,"syntology":null},{"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/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/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/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/automatically-generating-question-answer","slug":"automatically-generating-question-answer","title":"Automatically generating question-answer pairs for assessing basic reading comprehension in Swedish","date":"2022-11-28","arxiv_id":"2211.15568","repositories_listed":1,"syntology":null},{"url":"/paper/tempera-test-time-prompting-via-reinforcement","slug":"tempera-test-time-prompting-via-reinforcement","title":"TEMPERA: Test-Time Prompting via Reinforcement Learning","date":"2022-11-21","arxiv_id":"2211.11890","repositories_listed":1,"syntology":null},{"url":"/paper/world-knowledge-in-multiple-choice-reading","slug":"world-knowledge-in-multiple-choice-reading","title":"World Knowledge in Multiple Choice Reading Comprehension","date":"2022-11-13","arxiv_id":"2211.07040","repositories_listed":1,"syntology":null},{"url":"/paper/condaqa-a-contrastive-reading-comprehension","slug":"condaqa-a-contrastive-reading-comprehension","title":"CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation","date":"2022-11-01","arxiv_id":"2211.00295","repositories_listed":1,"syntology":null},{"url":"/paper/1cademy-causal-news-corpus-2022-enhance","slug":"1cademy-causal-news-corpus-2022-enhance","title":"1Cademy @ Causal News Corpus 2022: Enhance Causal Span Detection via Beam-Search-based Position Selector","date":"2022-10-31","arxiv_id":"2210.17157","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-multi-task-learning-for-abstractive","slug":"analyzing-multi-task-learning-for-abstractive","title":"Analyzing Multi-Task Learning for Abstractive Text Summarization","date":"2022-10-26","arxiv_id":"2210.14606","repositories_listed":1,"syntology":null},{"url":"/paper/idk-mrc-unanswerable-questions-for-indonesian","slug":"idk-mrc-unanswerable-questions-for-indonesian","title":"IDK-MRC: Unanswerable Questions for Indonesian Machine Reading Comprehension","date":"2022-10-25","arxiv_id":"2210.13778","repositories_listed":1,"syntology":null},{"url":"/paper/cascading-biases-investigating-the-effect-of","slug":"cascading-biases-investigating-the-effect-of","title":"Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models","date":"2022-10-24","arxiv_id":"2210.13439","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/lexical-generalization-improves-with-larger","slug":"lexical-generalization-improves-with-larger","title":"Lexical Generalization Improves with Larger Models and Longer Training","date":"2022-10-23","arxiv_id":"2210.12673","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/lexical-generalization-improves-with-larger#ran","syntology_url":"https://syntology.ai/paper/2210.12673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12673"}},"official":{"repos":["elronbandel/lexical-generalization"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/nerel-bio-a-dataset-of-biomedical-abstracts","slug":"nerel-bio-a-dataset-of-biomedical-abstracts","title":"NEREL-BIO: A Dataset of Biomedical Abstracts Annotated with Nested Named Entities","date":"2022-10-21","arxiv_id":"2210.11913","repositories_listed":1,"syntology":null},{"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/jecc-commonsense-reasoning-tasks-derived-from","slug":"jecc-commonsense-reasoning-tasks-derived-from","title":"JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions","date":"2022-10-18","arxiv_id":"2210.15456","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-pre-training-of-modular-prompt-for","slug":"multi-task-pre-training-of-modular-prompt-for","title":"Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning","date":"2022-10-14","arxiv_id":"2210.07565","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/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/instance-regularization-for-discriminative","slug":"instance-regularization-for-discriminative","title":"Instance Regularization for Discriminative Language Model Pre-training","date":"2022-10-11","arxiv_id":"2210.05471","repositories_listed":1,"syntology":null},{"url":"/paper/spaceqa-answering-questions-about-the-design","slug":"spaceqa-answering-questions-about-the-design","title":"SpaceQA: Answering Questions about the Design of Space Missions and Space Craft Concepts","date":"2022-10-07","arxiv_id":"2210.03422","repositories_listed":1,"syntology":null},{"url":"/paper/can-we-guide-a-multi-hop-reasoning-language","slug":"can-we-guide-a-multi-hop-reasoning-language","title":"Can We Guide a Multi-Hop Reasoning Language Model to Incrementally Learn at Each Single-Hop?","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dosea-a-domain-specific-entity-aware","slug":"dosea-a-domain-specific-entity-aware","title":"DoSEA: A Domain-specific Entity-aware Framework for Cross-Domain Named Entity Recogition","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/on-the-impact-of-speech-recognition-errors-in","slug":"on-the-impact-of-speech-recognition-errors-in","title":"On the Impact of Speech Recognition Errors in Passage Retrieval for Spoken Question Answering","date":"2022-09-26","arxiv_id":"2209.12944","repositories_listed":1,"syntology":null},{"url":"/paper/et5-a-novel-end-to-end-framework-for","slug":"et5-a-novel-end-to-end-framework-for","title":"ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension","date":"2022-09-23","arxiv_id":"2209.11484","repositories_listed":1,"syntology":null},{"url":"/paper/a-multi-turn-machine-reading-comprehension","slug":"a-multi-turn-machine-reading-comprehension","title":"A Multi-turn Machine Reading Comprehension Framework with Rethink Mechanism for Emotion-Cause Pair Extraction","date":"2022-09-16","arxiv_id":"2209.07972","repositories_listed":1,"syntology":null},{"url":"/paper/screenqa-large-scale-question-answer-pairs","slug":"screenqa-large-scale-question-answer-pairs","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","date":"2022-09-16","arxiv_id":"2209.08199","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/screenqa-large-scale-question-answer-pairs#ran","syntology_url":"https://syntology.ai/paper/2209.08199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.08199"}},"official":{"repos":["google-research-datasets/screen_qa"],"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"]}}}],"record_sha256":"6516323d1c3f6bdd8b6d2eca3589488421bc63f02c58d128ac832130eddad6aa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}