{"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/natural-questions","name":"Natural Questions","slug":"natural-questions","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":178,"papers_with_code":89,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/natural-questions-on-theoremqa","slug":"natural-questions-on-theoremqa","dataset":"TheoremQA","dataset_url":"/dataset/theoremqa","rows_in_archive":19,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT-4 (PoT)","paper_title":"TheoremQA: A Theorem-driven Question Answering dataset","paper_url":"/paper/theoremqa-a-theorem-driven-question-answering","paper_date":"2023-05-21","arxiv_id":"2305.12524","code_links":[{"title":"wenhuchen/theoremqa","url":"https://github.com/wenhuchen/theoremqa"}],"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/theoremqa-a-theorem-driven-question-answering#ran","syntology_url":"https://syntology.ai/paper/2305.12524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12524"}},"official":{"repos":["wenhuchen/theoremqa"],"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":["found_in_text","official"]}}}},{"leaderboard":"/sota/natural-questions-on-big-bench","slug":"natural-questions-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Gopher-280B (few-shot, k=64)","paper_title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","paper_url":"/paper/scaling-language-models-methods-analysis-1","paper_date":"2021-12-08","arxiv_id":"2112.11446","code_links":[{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"rvlopes/gloria","url":"https://github.com/rvlopes/gloria"},{"title":"bramiozo/PubScience","url":"https://github.com/bramiozo/PubScience"}],"syntology":null}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349},{"url":"/dataset/belebele","name":"Belebele","full_name":"","num_papers_in_archive":68},{"url":"/dataset/theoremqa","name":"TheoremQA","full_name":"TheoremQA","num_papers_in_archive":40},{"url":"/dataset/qampari","name":"QAMPARI","full_name":"","num_papers_in_archive":19},{"url":"/dataset/qasports","name":"QASports","full_name":"A Question Answering Dataset about Sports","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/general-knowledge","name":"General Knowledge"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":178,"of_with_code":89,"tagged_in_all":178,"counts":{"archive_papers_tagged":178,"with_a_code_link":89,"where_syntology_ran_a_sample":26,"not_listed_spam_title":0,"listed":178,"listed_where_code_ran":26,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":19,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":19,"listed_every_run_a_failure_of_syntologys_instrument":7,"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"},"items":[{"url":"/paper/leveraging-passage-retrieval-with-generative","slug":"leveraging-passage-retrieval-with-generative","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","date":"2020-07-02","arxiv_id":"2007.01282","repositories_listed":8,"syntology":null},{"url":"/paper/knowledge-guided-text-retrieval-and-reading","slug":"knowledge-guided-text-retrieval-and-reading","title":"Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering","date":"2019-11-10","arxiv_id":"1911.03868","repositories_listed":7,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/knowledge-guided-text-retrieval-and-reading#ran","syntology_url":"https://syntology.ai/paper/1911.03868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03868"}},"official":null}},{"url":"/paper/informer-transformer-likes-informed-attention","slug":"informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","arxiv_id":"2012.11747","repositories_listed":5,"syntology":null},{"url":"/paper/relevance-guided-supervision-for-openqa-with","slug":"relevance-guided-supervision-for-openqa-with","title":"Relevance-guided Supervision for OpenQA with ColBERT","date":"2020-07-01","arxiv_id":"2007.00814","repositories_listed":5,"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/relevance-guided-supervision-for-openqa-with#ran","syntology_url":"https://syntology.ai/paper/2007.00814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00814"}},"official":{"repos":["stanford-futuredata/ColBERT","stanfordnlp/ColBERT-QA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/designing-effective-sparse-expert-models","slug":"designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/designing-effective-sparse-expert-models#ran","syntology_url":"https://syntology.ai/paper/2202.08906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08906"}},"official":{"repos":["tensorflow/mesh"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/tempoqr-temporal-question-reasoning-over","slug":"tempoqr-temporal-question-reasoning-over","title":"TempoQR: Temporal Question Reasoning over Knowledge Graphs","date":"2021-12-10","arxiv_id":"2112.05785","repositories_listed":3,"syntology":null},{"url":"/paper/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/autoqa-from-databases-to-qa-semantic-parsers","slug":"autoqa-from-databases-to-qa-semantic-parsers","title":"AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data","date":"2020-10-09","arxiv_id":"2010.04806","repositories_listed":3,"syntology":{"n":26,"n_ran":13,"n_constructed":2,"n_ran_checked":10,"n_instrument":3,"n_unverified":13,"n_honours":1,"n_violates":4,"n_no_contract":5,"n_pointer_only":26,"phrase":"13 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 4 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/autoqa-from-databases-to-qa-semantic-parsers#ran","syntology_url":"https://syntology.ai/paper/2010.04806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04806"}},"official":{"repos":["stanford-oval/genienlp","stanford-oval/genie-toolkit","stanford-oval/schema2qa"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":2,"n_ran_no_instrument_failure":10,"n_unverified":13,"ran_from_kinds":["official"]}}},{"url":"/paper/event-extraction-by-answering-almost-natural","slug":"event-extraction-by-answering-almost-natural","title":"Event Extraction by Answering (Almost) Natural Questions","date":"2020-04-28","arxiv_id":"2004.13625","repositories_listed":3,"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":0,"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/event-extraction-by-answering-almost-natural#ran","syntology_url":"https://syntology.ai/paper/2004.13625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13625"}},"official":{"repos":["xinyadu/eeqa"],"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":["listed","official"]}}},{"url":"/paper/a-bert-baseline-for-the-natural-questions","slug":"a-bert-baseline-for-the-natural-questions","title":"A BERT Baseline for the Natural Questions","date":"2019-01-24","arxiv_id":"1901.08634","repositories_listed":3,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/a-bert-baseline-for-the-natural-questions#ran","syntology_url":"https://syntology.ai/paper/1901.08634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08634"}},"official":{"repos":["google-research/language"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/lightweight-and-direct-document-relevance","slug":"lightweight-and-direct-document-relevance","title":"Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval","date":"2025-04-07","arxiv_id":"2504.05181","repositories_listed":2,"syntology":null},{"url":"/paper/dr-spider-a-diagnostic-evaluation-benchmark","slug":"dr-spider-a-diagnostic-evaluation-benchmark","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","date":"2023-01-21","arxiv_id":"2301.08881","repositories_listed":2,"syntology":null},{"url":"/paper/dptdr-deep-prompt-tuning-for-dense-passage","slug":"dptdr-deep-prompt-tuning-for-dense-passage","title":"DPTDR: Deep Prompt Tuning for Dense Passage Retrieval","date":"2022-08-24","arxiv_id":"2208.11503","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-learning-with-retrieval-augmented","slug":"few-shot-learning-with-retrieval-augmented","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","date":"2022-08-05","arxiv_id":"2208.03299","repositories_listed":2,"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":2,"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/few-shot-learning-with-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2208.03299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03299"}},"official":{"repos":["facebookresearch/atlas"],"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/qampari-an-open-domain-question-answering","slug":"qampari-an-open-domain-question-answering","title":"QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs","date":"2022-05-25","arxiv_id":"2205.12665","repositories_listed":2,"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/qampari-an-open-domain-question-answering#ran","syntology_url":"https://syntology.ai/paper/2205.12665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12665"}},"official":null}},{"url":"/paper/would-you-ask-it-that-way-measuring-and","slug":"would-you-ask-it-that-way-measuring-and","title":"Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering","date":"2022-05-25","arxiv_id":"2205.12768","repositories_listed":2,"syntology":null},{"url":"/paper/continual-learning-with-knowledge-transfer","slug":"continual-learning-with-knowledge-transfer","title":"Continual Learning with Knowledge Transfer for Sentiment Classification","date":"2021-12-18","arxiv_id":"2112.10021","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-training-of-neural-retrievers-for","slug":"end-to-end-training-of-neural-retrievers-for","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","date":"2021-01-02","arxiv_id":"2101.00408","repositories_listed":2,"syntology":null},{"url":"/paper/mkqa-a-linguistically-diverse-benchmark-for","slug":"mkqa-a-linguistically-diverse-benchmark-for","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","date":"2020-07-30","arxiv_id":"2007.15207","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/mkqa-a-linguistically-diverse-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2007.15207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.15207"}},"official":{"repos":["apple/ml-mkqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tanda-transfer-and-adapt-pre-trained","slug":"tanda-transfer-and-adapt-pre-trained","title":"TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection","date":"2019-11-11","arxiv_id":"1911.04118","repositories_listed":2,"syntology":null},{"url":"/paper/generating-natural-questions-about-an-image","slug":"generating-natural-questions-about-an-image","title":"Generating Natural Questions About an Image","date":"2016-03-19","arxiv_id":"1603.06059","repositories_listed":2,"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/generating-natural-questions-about-an-image#ran","syntology_url":"https://syntology.ai/paper/1603.06059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.06059"}},"official":null}},{"url":"/paper/constructing-and-evaluating-declarative-rag","slug":"constructing-and-evaluating-declarative-rag","title":"Constructing and Evaluating Declarative RAG Pipelines in PyTerrier","date":"2025-06-12","arxiv_id":"2506.10802","repositories_listed":1,"syntology":null},{"url":"/paper/poisonarena-uncovering-competing-poisoning","slug":"poisonarena-uncovering-competing-poisoning","title":"PoisonArena: Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation","date":"2025-05-18","arxiv_id":"2505.12574","repositories_listed":1,"syntology":null},{"url":"/paper/grada-graph-based-reranker-against","slug":"grada-graph-based-reranker-against","title":"GRADA: Graph-based Reranker against Adversarial Documents Attack","date":"2025-05-12","arxiv_id":"2505.07546","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-vs-fine-tuning-a-reproducibility","slug":"pre-training-vs-fine-tuning-a-reproducibility","title":"Pre-training vs. Fine-tuning: A Reproducibility Study on Dense Retrieval Knowledge Acquisition","date":"2025-05-12","arxiv_id":"2505.07166","repositories_listed":1,"syntology":null},{"url":"/paper/s1-bench-a-simple-benchmark-for-evaluating","slug":"s1-bench-a-simple-benchmark-for-evaluating","title":"S1-Bench: A Simple Benchmark for Evaluating System 1 Thinking Capability of Large Reasoning Models","date":"2025-04-14","arxiv_id":"2504.10368","repositories_listed":1,"syntology":null},{"url":"/paper/dragonverseqa-open-domain-long-form-context","slug":"dragonverseqa-open-domain-long-form-context","title":"DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering","date":"2024-12-21","arxiv_id":"2412.16694","repositories_listed":1,"syntology":null},{"url":"/paper/rag-confusionqa-a-benchmark-for-evaluating","slug":"rag-confusionqa-a-benchmark-for-evaluating","title":"ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions","date":"2024-10-18","arxiv_id":"2410.14567","repositories_listed":1,"syntology":null},{"url":"/paper/fastfid-improve-inference-efficiency-of-open","slug":"fastfid-improve-inference-efficiency-of-open","title":"FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection","date":"2024-08-12","arxiv_id":"2408.06333","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/fastfid-improve-inference-efficiency-of-open#ran","syntology_url":"https://syntology.ai/paper/2408.06333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06333"}},"official":{"repos":["thunlp/fastfid"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/llasa-large-multimodal-agent-for-human","slug":"llasa-large-multimodal-agent-for-human","title":"LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors","date":"2024-06-20","arxiv_id":"2406.14498","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llasa-large-multimodal-agent-for-human#ran","syntology_url":"https://syntology.ai/paper/2406.14498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14498"}},"official":{"repos":["bashlab/llasa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dart-math-difficulty-aware-rejection-tuning-1","slug":"dart-math-difficulty-aware-rejection-tuning-1","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","date":"2024-06-18","arxiv_id":"2407.13690","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}},"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/re-rag-improving-open-domain-qa-performance","slug":"re-rag-improving-open-domain-qa-performance","title":"RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05794","repositories_listed":1,"syntology":null},{"url":"/paper/gnn-rag-graph-neural-retrieval-for-large","slug":"gnn-rag-graph-neural-retrieval-for-large","title":"GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning","date":"2024-05-30","arxiv_id":"2405.20139","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":1,"n_no_contract":1,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gnn-rag-graph-neural-retrieval-for-large#ran","syntology_url":"https://syntology.ai/paper/2405.20139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20139"}},"official":{"repos":["cmavro/gnn-rag"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/layer-skip-enabling-early-exit-inference-and","slug":"layer-skip-enabling-early-exit-inference-and","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","date":"2024-04-25","arxiv_id":"2404.16710","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/layer-skip-enabling-early-exit-inference-and#ran","syntology_url":"https://syntology.ai/paper/2404.16710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16710"}},"official":{"repos":["facebookresearch/layerskip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/kazqad-kazakh-open-domain-question-answering","slug":"kazqad-kazakh-open-domain-question-answering","title":"KazQAD: Kazakh Open-Domain Question Answering Dataset","date":"2024-04-06","arxiv_id":"2404.04487","repositories_listed":1,"syntology":null},{"url":"/paper/multi-granularity-guided-fusion-in-decoder","slug":"multi-granularity-guided-fusion-in-decoder","title":"Multi-Granularity Guided Fusion-in-Decoder","date":"2024-04-03","arxiv_id":"2404.02581","repositories_listed":1,"syntology":null},{"url":"/paper/clapnq-cohesive-long-form-answers-from","slug":"clapnq-cohesive-long-form-answers-from","title":"CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems","date":"2024-04-02","arxiv_id":"2404.02103","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-cross-lingual-open-domain","slug":"pre-training-cross-lingual-open-domain","title":"Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision","date":"2024-02-26","arxiv_id":"2402.16508","repositories_listed":1,"syntology":null},{"url":"/paper/acid-abstractive-content-based-ids-for","slug":"acid-abstractive-content-based-ids-for","title":"Summarization-Based Document IDs for Generative Retrieval with Language Models","date":"2023-11-14","arxiv_id":"2311.08593","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/acid-abstractive-content-based-ids-for#ran","syntology_url":"https://syntology.ai/paper/2311.08593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08593"}},"official":{"repos":["lihaoxin2020/summarization-based-document-ids-for-generative-retrieval"],"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/jade-a-linguistic-based-safety-evaluation","slug":"jade-a-linguistic-based-safety-evaluation","title":"JADE: A Linguistics-based Safety Evaluation Platform for Large Language Models","date":"2023-11-01","arxiv_id":"2311.00286","repositories_listed":1,"syntology":null},{"url":"/paper/poisoning-retrieval-corpora-by-injecting","slug":"poisoning-retrieval-corpora-by-injecting","title":"Poisoning Retrieval Corpora by Injecting Adversarial Passages","date":"2023-10-29","arxiv_id":"2310.19156","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/poisoning-retrieval-corpora-by-injecting#ran","syntology_url":"https://syntology.ai/paper/2310.19156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19156"}},"official":{"repos":["princeton-nlp/corpus-poisoning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/model-enhanced-vector-index","slug":"model-enhanced-vector-index","title":"Model-enhanced Vector Index","date":"2023-09-23","arxiv_id":"2309.13335","repositories_listed":1,"syntology":null},{"url":"/paper/on-monotonic-aggregation-for-open-domain-qa","slug":"on-monotonic-aggregation-for-open-domain-qa","title":"On Monotonic Aggregation for Open-domain QA","date":"2023-08-08","arxiv_id":"2308.04176","repositories_listed":1,"syntology":null},{"url":"/paper/trac-trustworthy-retrieval-augmented-chatbot","slug":"trac-trustworthy-retrieval-augmented-chatbot","title":"TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction","date":"2023-07-07","arxiv_id":"2307.04642","repositories_listed":1,"syntology":null},{"url":"/paper/adanns-a-framework-for-adaptive-semantic","slug":"adanns-a-framework-for-adaptive-semantic","title":"AdANNS: A Framework for Adaptive Semantic Search","date":"2023-05-30","arxiv_id":"2305.19435","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 1 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/adanns-a-framework-for-adaptive-semantic#ran","syntology_url":"https://syntology.ai/paper/2305.19435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19435"}},"official":{"repos":["raivnlab/adanns"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exploiting-abstract-meaning-representation","slug":"exploiting-abstract-meaning-representation","title":"Exploiting Abstract Meaning Representation for Open-Domain Question Answering","date":"2023-05-26","arxiv_id":"2305.17050","repositories_listed":1,"syntology":null},{"url":"/paper/rfid-towards-rational-fusion-in-decoder-for","slug":"rfid-towards-rational-fusion-in-decoder-for","title":"RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering","date":"2023-05-26","arxiv_id":"2305.17041","repositories_listed":1,"syntology":null},{"url":"/paper/term-sets-can-be-strong-document-identifiers","slug":"term-sets-can-be-strong-document-identifiers","title":"Generative Retrieval via Term Set Generation","date":"2023-05-23","arxiv_id":"2305.13859","repositories_listed":1,"syntology":null},{"url":"/paper/critic-large-language-models-can-self-correct","slug":"critic-large-language-models-can-self-correct","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","date":"2023-05-19","arxiv_id":"2305.11738","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/critic-large-language-models-can-self-correct#ran","syntology_url":"https://syntology.ai/paper/2305.11738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11738"}},"official":{"repos":["microsoft/ProphetNet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/meeqa-natural-questions-in-meeting","slug":"meeqa-natural-questions-in-meeting","title":"MeeQA: Natural Questions in Meeting Transcripts","date":"2023-05-15","arxiv_id":"2305.08502","repositories_listed":1,"syntology":null},{"url":"/paper/neural-gromov-wasserstein-optimal-transport","slug":"neural-gromov-wasserstein-optimal-transport","title":"Uncovering Challenges of Solving the Continuous Gromov-Wasserstein Problem","date":"2023-03-10","arxiv_id":"2303.05978","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-effectiveness-of-parameter-efficient","slug":"on-the-effectiveness-of-parameter-efficient","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","date":"2022-11-28","arxiv_id":"2211.15583","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/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/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/prod-progressive-distillation-for-dense","slug":"prod-progressive-distillation-for-dense","title":"PROD: Progressive Distillation for Dense Retrieval","date":"2022-09-27","arxiv_id":"2209.13335","repositories_listed":1,"syntology":null},{"url":"/paper/multispanqa-a-dataset-for-multi-span-question","slug":"multispanqa-a-dataset-for-multi-span-question","title":"MultiSpanQA: A Dataset for Multi-Span Question Answering","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unfooling-perturbation-based-post-hoc","slug":"unfooling-perturbation-based-post-hoc","title":"Unfooling Perturbation-Based Post Hoc Explainers","date":"2022-05-29","arxiv_id":"2205.14772","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/unfooling-perturbation-based-post-hoc#ran","syntology_url":"https://syntology.ai/paper/2205.14772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14772"}},"official":{"repos":["craymichael/unfooling"],"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/table-retrieval-may-not-necessitate-table","slug":"table-retrieval-may-not-necessitate-table","title":"Table Retrieval May Not Necessitate Table-specific Model Design","date":"2022-05-19","arxiv_id":"2205.09843","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"11 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; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/table-retrieval-may-not-necessitate-table#ran","syntology_url":"https://syntology.ai/paper/2205.09843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09843"}},"official":{"repos":["zorazrw/nqt-retrieval"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/how-do-we-answer-complex-questions-discourse-1","slug":"how-do-we-answer-complex-questions-discourse-1","title":"How Do We Answer Complex Questions: Discourse Structure of Long-form Answers","date":"2022-03-21","arxiv_id":"2203.11048","repositories_listed":1,"syntology":null},{"url":"/paper/asyncval-a-toolkit-for-asynchronously","slug":"asyncval-a-toolkit-for-asynchronously","title":"Asyncval: A Toolkit for Asynchronously Validating Dense Retriever Checkpoints during Training","date":"2022-02-25","arxiv_id":"2202.12510","repositories_listed":1,"syntology":null},{"url":"/paper/text-and-code-embeddings-by-contrastive-pre","slug":"text-and-code-embeddings-by-contrastive-pre","title":"Text and Code Embeddings by Contrastive Pre-Training","date":"2022-01-24","arxiv_id":"2201.10005","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-commonsense-question-answering-with","slug":"zero-shot-commonsense-question-answering-with","title":"Zero-shot Commonsense Question Answering with Cloze Translation and Consistency Optimization","date":"2022-01-01","arxiv_id":"2201.00136","repositories_listed":1,"syntology":null},{"url":"/paper/duqm-a-chinese-dataset-of-linguistically","slug":"duqm-a-chinese-dataset-of-linguistically","title":"DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models","date":"2021-12-16","arxiv_id":"2112.08609","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-open-book-question-answering","slug":"zero-shot-open-book-question-answering","title":"Zero-Shot Open-Book Question Answering","date":"2021-11-22","arxiv_id":"2111.11520","repositories_listed":1,"syntology":null},{"url":"/paper/whats-in-a-name-answer-equivalence-for-open","slug":"whats-in-a-name-answer-equivalence-for-open","title":"What’s in a Name? Answer Equivalence For Open-Domain Question Answering","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/open-domain-question-answering-over-virtual","slug":"open-domain-question-answering-over-virtual","title":"Open Domain Question Answering with A Unified Knowledge Interface","date":"2021-10-16","arxiv_id":"2110.08417","repositories_listed":1,"syntology":null},{"url":"/paper/rocketqav2-a-joint-training-method-for-dense","slug":"rocketqav2-a-joint-training-method-for-dense","title":"RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking","date":"2021-10-14","arxiv_id":"2110.07367","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-retriever-ranker-for-dense-text","slug":"adversarial-retriever-ranker-for-dense-text","title":"Adversarial Retriever-Ranker for dense text retrieval","date":"2021-10-07","arxiv_id":"2110.03611","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adversarial-retriever-ranker-for-dense-text#ran","syntology_url":"https://syntology.ai/paper/2110.03611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03611"}},"official":{"repos":["microsoft/ar2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/what-s-in-a-name-answer-equivalence-for-open","slug":"what-s-in-a-name-answer-equivalence-for-open","title":"What's in a Name? Answer Equivalence For Open-Domain Question Answering","date":"2021-09-11","arxiv_id":"2109.05289","repositories_listed":1,"syntology":null},{"url":"/paper/challenges-in-generalization-in-open-domain","slug":"challenges-in-generalization-in-open-domain","title":"Challenges in Generalization in Open Domain Question Answering","date":"2021-09-02","arxiv_id":"2109.01156","repositories_listed":1,"syntology":null},{"url":"/paper/pair-leveraging-passage-centric-similarity","slug":"pair-leveraging-passage-centric-similarity","title":"PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval","date":"2021-08-13","arxiv_id":"2108.06027","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-passage-retrieval-with-hashing-for","slug":"efficient-passage-retrieval-with-hashing-for","title":"Efficient Passage Retrieval with Hashing for Open-domain Question Answering","date":"2021-06-02","arxiv_id":"2106.00882","repositories_listed":1,"syntology":null},{"url":"/paper/corpus-level-evaluation-for-event-qa-the","slug":"corpus-level-evaluation-for-event-qa-the","title":"Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence","date":"2021-05-27","arxiv_id":"2105.12936","repositories_listed":1,"syntology":null},{"url":"/paper/back-training-excels-self-training-at","slug":"back-training-excels-self-training-at","title":"Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval","date":"2021-04-18","arxiv_id":"2104.08801","repositories_listed":1,"syntology":null},{"url":"/paper/open-domain-question-answering-over-tables","slug":"open-domain-question-answering-over-tables","title":"Open Domain Question Answering over Tables via Dense Retrieval","date":"2021-03-22","arxiv_id":"2103.12011","repositories_listed":1,"syntology":null},{"url":"/paper/reader-guided-passage-reranking-for-open","slug":"reader-guided-passage-reranking-for-open","title":"Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering","date":"2021-01-01","arxiv_id":"2101.00294","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reader-guided-passage-reranking-for-open#ran","syntology_url":"https://syntology.ai/paper/2101.00294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00294"}},"official":{"repos":["morningmoni/GAR"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/reconsider-re-ranking-using-span-focused","slug":"reconsider-re-ranking-using-span-focused","title":"RECONSIDER: Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answering","date":"2020-10-21","arxiv_id":"2010.10757","repositories_listed":1,"syntology":null},{"url":"/paper/rocketqa-an-optimized-training-approach-to","slug":"rocketqa-an-optimized-training-approach-to","title":"RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering","date":"2020-10-16","arxiv_id":"2010.08191","repositories_listed":1,"syntology":null},{"url":"/paper/generation-augmented-retrieval-for-open","slug":"generation-augmented-retrieval-for-open","title":"Generation-Augmented Retrieval for Open-domain Question Answering","date":"2020-09-17","arxiv_id":"2009.08553","repositories_listed":1,"syntology":null},{"url":"/paper/qed-a-framework-and-dataset-for-explanations","slug":"qed-a-framework-and-dataset-for-explanations","title":"QED: A Framework and Dataset for Explanations in Question Answering","date":"2020-09-08","arxiv_id":"2009.06354","repositories_listed":1,"syntology":null},{"url":"/paper/c3vqg-category-consistent-cyclic-visual","slug":"c3vqg-category-consistent-cyclic-visual","title":"C3VQG: Category Consistent Cyclic Visual Question Generation","date":"2020-05-15","arxiv_id":"2005.07771","repositories_listed":1,"syntology":null},{"url":"/paper/document-modeling-with-graph-attention","slug":"document-modeling-with-graph-attention","title":"Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension","date":"2020-05-12","arxiv_id":"2005.05806","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":8,"n_ran_checked":8,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":16,"phrase":"8 ran (of which 8 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) · 8 unverified; every one of the 8 samples that ran constructed an object rather than computing a result","sample_list":"/paper/document-modeling-with-graph-attention#ran","syntology_url":"https://syntology.ai/paper/2005.05806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05806"}},"official":{"repos":["DancingSoul/NQ_BERT-DM"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/span-selection-pre-training-for-question","slug":"span-selection-pre-training-for-question","title":"Span Selection Pre-training for Question Answering","date":"2019-09-09","arxiv_id":"1909.04120","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/span-selection-pre-training-for-question#ran","syntology_url":"https://syntology.ai/paper/1909.04120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04120"}},"official":{"repos":["IBM/span-selection-pretraining"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-question-answering-by-cloze","slug":"unsupervised-question-answering-by-cloze","title":"Unsupervised Question Answering by Cloze Translation","date":"2019-06-12","arxiv_id":"1906.04980","repositories_listed":1,"syntology":null},{"url":"/paper/natural-questions-a-benchmark-for-question","slug":"natural-questions-a-benchmark-for-question","title":"Natural Questions: a Benchmark for Question Answering Research","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-differential-network-for-visual","slug":"multimodal-differential-network-for-visual","title":"Multimodal Differential Network for Visual Question Generation","date":"2018-08-12","arxiv_id":"1808.03986","repositories_listed":1,"syntology":null},{"url":"/paper/cover-learning-covariate-specific-vector","slug":"cover-learning-covariate-specific-vector","title":"CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions","date":"2018-02-21","arxiv_id":"1802.07839","repositories_listed":1,"syntology":null},{"url":"/paper/sampling-from-large-graphs","slug":"sampling-from-large-graphs","title":"Sampling From Large Graphs","date":"2006-08-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"2506-03100","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","date":"2025-06-03","arxiv_id":"2506.03100","repositories_listed":0,"syntology":null},{"url":null,"slug":"craft-training-free-cascaded-retrieval-for","title":"CRAFT: Training-Free Cascaded Retrieval for Tabular QA","date":"2025-05-21","arxiv_id":"2505.14984","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-defensive-thought-structured","title":"Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption","date":"2025-04-29","arxiv_id":"2504.20769","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-fully-exploiting-llm-internal-states","title":"Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception","date":"2025-02-17","arxiv_id":"2502.11677","repositories_listed":0,"syntology":null},{"url":null,"slug":"cachefocus-dynamic-cache-re-positioning-for","title":"CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation","date":"2025-02-16","arxiv_id":"2502.11101","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-knowledge-integration-in-retrieval","title":"Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection","date":"2025-02-10","arxiv_id":"2502.06148","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-rag-models-with-graph-structures","title":"Advanced RAG Models with Graph Structures: Optimizing Complex Knowledge Reasoning and Text Generation","date":"2024-11-06","arxiv_id":"2411.03572","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-explanations-and-self-explanations-for","title":"Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs","date":"2024-09-18","arxiv_id":"2409.13764","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-context-faithfulness-in-large","title":"Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style","date":"2024-09-17","arxiv_id":"2409.10955","repositories_listed":0,"syntology":null},{"url":null,"slug":"autorag-hp-automatic-online-hyper-parameter","title":"AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation","date":"2024-06-27","arxiv_id":"2406.19251","repositories_listed":0,"syntology":null},{"url":null,"slug":"unifying-multimodal-retrieval-via-document","title":"Unifying Multimodal Retrieval via Document Screenshot Embedding","date":"2024-06-17","arxiv_id":"2406.11251","repositories_listed":0,"syntology":null}],"syntology_records":27,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/natural-questions-on-theoremqa","since_archive":"/sota/natural-questions-on-theoremqa#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":26,"papers_where_code_ran_first_page":"/task/natural-questions/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/natural-questions/papers/2","json":"/task/natural-questions/papers/2.json","rows":78},{"order":"ran","page":1,"of":1,"url":"/task/natural-questions/papers/ran/1","json":"/task/natural-questions/papers/ran/1.json","rows":26}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"5bc39f1e5873f1fcf005abe5d7be72f4398b96bf66473b17397a56cb42882cca","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}