{"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/long-form-question-answering","name":"Long Form Question Answering","slug":"long-form-question-answering","description_markdown":"Long-form question answering is a task requiring elaborate and in-depth answers to open-ended questions.","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":61,"papers_with_code":32,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":[],"datasets":[{"url":"/dataset/eli5","name":"ELI5","full_name":"ELI5","num_papers_in_archive":158},{"url":"/dataset/quality","name":"QuALITY","full_name":"Question Answering with Long Input Texts, Yes!","num_papers_in_archive":98},{"url":"/dataset/lleqa","name":"LLeQA","full_name":"Long-form Legal Question Answering","num_papers_in_archive":3},{"url":"/dataset/darai","name":"DARai","full_name":"Daily Activity Recordings for AI and ML applications","num_papers_in_archive":1},{"url":"/dataset/mminstruct-gpt4v","name":"MMInstruct-GPT4V","full_name":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/question-answering","name":"Question Answering"}],"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":1,"rows_per_page":100,"shown":61,"of":61,"of_with_code":32,"tagged_in_all":61,"counts":{"archive_papers_tagged":61,"with_a_code_link":32,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":61,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/eli5-long-form-question-answering","slug":"eli5-long-form-question-answering","title":"ELI5: Long Form Question Answering","date":"2019-07-22","arxiv_id":"1907.09190","repositories_listed":3,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/eli5-long-form-question-answering#ran","syntology_url":"https://syntology.ai/paper/1907.09190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.09190"}},"official":{"repos":["facebookresearch/ELI5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/semqa-semi-extractive-multi-source-question","slug":"semqa-semi-extractive-multi-source-question","title":"SEMQA: Semi-Extractive Multi-Source Question Answering","date":"2023-11-08","arxiv_id":"2311.04886","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-one-preference-for-all-multi-objective","slug":"beyond-one-preference-for-all-multi-objective","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","date":"2023-10-05","arxiv_id":"2310.03708","repositories_listed":2,"syntology":null},{"url":"/paper/longform-optimizing-instruction-tuning-for","slug":"longform-optimizing-instruction-tuning-for","title":"LongForm: Effective Instruction Tuning with Reverse Instructions","date":"2023-04-17","arxiv_id":"2304.08460","repositories_listed":2,"syntology":null},{"url":"/paper/hurdles-to-progress-in-long-form-question","slug":"hurdles-to-progress-in-long-form-question","title":"Hurdles to Progress in Long-form Question Answering","date":"2021-03-10","arxiv_id":"2103.06332","repositories_listed":2,"syntology":null},{"url":"/paper/generationprograms-fine-grained-attribution","slug":"generationprograms-fine-grained-attribution","title":"GenerationPrograms: Fine-grained Attribution with Executable Programs","date":"2025-06-17","arxiv_id":"2506.14580","repositories_listed":1,"syntology":null},{"url":"/paper/atomic-consistency-preference-optimization","slug":"atomic-consistency-preference-optimization","title":"Atomic Consistency Preference Optimization for Long-Form Question Answering","date":"2025-05-14","arxiv_id":"2505.09039","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-evaluating-long-form","slug":"an-empirical-study-of-evaluating-long-form","title":"An Empirical Study of Evaluating Long-form Question Answering","date":"2025-04-25","arxiv_id":"2504.18413","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-influence-of-context-size-and-model","slug":"on-the-influence-of-context-size-and-model","title":"On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems","date":"2025-02-20","arxiv_id":"2502.14759","repositories_listed":1,"syntology":null},{"url":"/paper/how-much-do-llms-hallucinate-across-languages","slug":"how-much-do-llms-hallucinate-across-languages","title":"How Much Do LLMs Hallucinate across Languages? On Multilingual Estimation of LLM Hallucination in the Wild","date":"2025-02-18","arxiv_id":"2502.12769","repositories_listed":1,"syntology":null},{"url":"/paper/selfcite-self-supervised-alignment-for","slug":"selfcite-self-supervised-alignment-for","title":"SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models","date":"2025-02-13","arxiv_id":"2502.09604","repositories_listed":1,"syntology":null},{"url":"/paper/a-claim-decomposition-benchmark-for-long-form","slug":"a-claim-decomposition-benchmark-for-long-form","title":"A Claim Decomposition Benchmark for Long-form Answer Verification","date":"2024-10-16","arxiv_id":"2410.12558","repositories_listed":1,"syntology":null},{"url":"/paper/ancient-wisdom-modern-tools-exploring","slug":"ancient-wisdom-modern-tools-exploring","title":"Ancient Wisdom, Modern Tools: Exploring Retrieval-Augmented LLMs for Ancient Indian Philosophy","date":"2024-08-21","arxiv_id":"2408.11903","repositories_listed":1,"syntology":null},{"url":"/paper/putting-people-in-llms-shoes-generating","slug":"putting-people-in-llms-shoes-generating","title":"Putting People in LLMs' Shoes: Generating Better Answers via Question Rewriter","date":"2024-08-20","arxiv_id":"2408.10573","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-hallucination-detection-and-1","slug":"fine-grained-hallucination-detection-and-1","title":"Localizing and Mitigating Errors in Long-form Question Answering","date":"2024-07-16","arxiv_id":"2407.11930","repositories_listed":1,"syntology":null},{"url":"/paper/anah-v2-scaling-analytical-hallucination","slug":"anah-v2-scaling-analytical-hallucination","title":"ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models","date":"2024-07-05","arxiv_id":"2407.04693","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 3 unverified","sample_list":"/paper/anah-v2-scaling-analytical-hallucination#ran","syntology_url":"https://syntology.ai/paper/2407.04693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04693"}},"official":{"repos":["open-compass/anah"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/calmqa-exploring-culturally-specific-long","slug":"calmqa-exploring-culturally-specific-long","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","date":"2024-06-25","arxiv_id":"2406.17761","repositories_listed":1,"syntology":null},{"url":"/paper/olaph-improving-factuality-in-biomedical-long","slug":"olaph-improving-factuality-in-biomedical-long","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","date":"2024-05-21","arxiv_id":"2405.12701","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/attribute-first-then-generate-locally","slug":"attribute-first-then-generate-locally","title":"Attribute First, then Generate: Locally-attributable Grounded Text Generation","date":"2024-03-25","arxiv_id":"2403.17104","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/attribute-first-then-generate-locally#ran","syntology_url":"https://syntology.ai/paper/2403.17104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17104"}},"official":{"repos":["lovodkin93/attribute-first-then-generate"],"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/alarm-align-language-models-via-hierarchical","slug":"alarm-align-language-models-via-hierarchical","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling","date":"2024-03-11","arxiv_id":"2403.06754","repositories_listed":1,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 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; 5 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/alarm-align-language-models-via-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2403.06754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06754"}},"official":{"repos":["halfrot/ALaRM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/kg-rank-enhancing-large-language-models-for","slug":"kg-rank-enhancing-large-language-models-for","title":"KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques","date":"2024-03-09","arxiv_id":"2403.05881","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":5,"phrase":"3 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/kg-rank-enhancing-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2403.05881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05881"}},"official":{"repos":["yangrui525/kg-rank"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-replaces-supervision-query","slug":"reinforcement-replaces-supervision-query","title":"Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement Learning","date":"2023-11-29","arxiv_id":"2311.17514","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-human-feedback-gives-better","slug":"fine-grained-human-feedback-gives-better","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","date":"2023-06-02","arxiv_id":"2306.01693","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/fine-grained-human-feedback-gives-better#ran","syntology_url":"https://syntology.ai/paper/2306.01693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01693"}},"official":null}},{"url":"/paper/concise-answers-to-complex-questions","slug":"concise-answers-to-complex-questions","title":"Concise Answers to Complex Questions: Summarization of Long-form Answers","date":"2023-05-30","arxiv_id":"2305.19271","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 2 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) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/concise-answers-to-complex-questions#ran","syntology_url":"https://syntology.ai/paper/2305.19271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19271"}},"official":{"repos":["acpotluri/lfqa_summary"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-critical-evaluation-of-evaluations-for-long","slug":"a-critical-evaluation-of-evaluations-for-long","title":"A Critical Evaluation of Evaluations for Long-form Question Answering","date":"2023-05-29","arxiv_id":"2305.18201","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-sentence-union-generation-as-a","slug":"revisiting-sentence-union-generation-as-a","title":"Revisiting Sentence Union Generation as a Testbed for Text Consolidation","date":"2023-05-24","arxiv_id":"2305.15605","repositories_listed":1,"syntology":null},{"url":"/paper/webcpm-interactive-web-search-for-chinese","slug":"webcpm-interactive-web-search-for-chinese","title":"WebCPM: Interactive Web Search for Chinese Long-form Question Answering","date":"2023-05-11","arxiv_id":"2305.06849","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/webcpm-interactive-web-search-for-chinese#ran","syntology_url":"https://syntology.ai/paper/2305.06849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06849"}},"official":{"repos":["thunlp/webcpm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/search-in-the-chain-towards-the-accurate","slug":"search-in-the-chain-towards-the-accurate","title":"Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks","date":"2023-04-28","arxiv_id":"2304.14732","repositories_listed":1,"syntology":null},{"url":"/paper/d2s-document-to-slide-generation-via-query","slug":"d2s-document-to-slide-generation-via-query","title":"D2S: Document-to-Slide Generation Via Query-Based Text Summarization","date":"2021-05-08","arxiv_id":"2105.03664","repositories_listed":1,"syntology":null},{"url":"/paper/controllable-generation-from-pre-trained","slug":"controllable-generation-from-pre-trained","title":"Controllable Generation from Pre-trained Language Models via Inverse Prompting","date":"2021-03-19","arxiv_id":"2103.10685","repositories_listed":1,"syntology":null},{"url":"/paper/using-local-knowledge-graph-construction-to","slug":"using-local-knowledge-graph-construction-to","title":"Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs","date":"2019-10-18","arxiv_id":"1910.08435","repositories_listed":1,"syntology":null},{"url":null,"slug":"improving-reliability-and-explainability-of","title":"Improving Reliability and Explainability of Medical Question Answering through Atomic Fact Checking in Retrieval-Augmented LLMs","date":"2025-05-30","arxiv_id":"2505.24830","repositories_listed":0,"syntology":null},{"url":null,"slug":"lamp-qa-a-benchmark-for-personalized-long","title":"LaMP-QA: A Benchmark for Personalized Long-form Question Answering","date":"2025-05-30","arxiv_id":"2506.00137","repositories_listed":0,"syntology":null},{"url":null,"slug":"mamm-refine-a-recipe-for-improving","title":"MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration","date":"2025-03-19","arxiv_id":"2503.15272","repositories_listed":0,"syntology":null},{"url":null,"slug":"generate-discriminate-evolve-enhancing","title":"Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution","date":"2025-03-03","arxiv_id":"2503.01695","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-contextual-faithfulness-of-large","title":"Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization","date":"2025-01-23","arxiv_id":"2501.13573","repositories_listed":0,"syntology":null},{"url":null,"slug":"to-retrieve-or-not-to-retrieve-uncertainty","title":"To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generation","date":"2025-01-16","arxiv_id":"2501.09292","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieving-contextual-information-for-long","title":"Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision","date":"2024-10-11","arxiv_id":"2410.08623","repositories_listed":0,"syntology":null},{"url":null,"slug":"calf-benchmarking-evaluation-of-lfqa-using","title":"CALF: Benchmarking Evaluation of LFQA Using Chinese Examinations","date":"2024-10-02","arxiv_id":"2410.01945","repositories_listed":0,"syntology":null},{"url":null,"slug":"ground-every-sentence-improving-retrieval","title":"Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation","date":"2024-07-01","arxiv_id":"2407.01796","repositories_listed":0,"syntology":null},{"url":null,"slug":"forag-factuality-optimized-retrieval","title":"FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering","date":"2024-06-19","arxiv_id":"2406.13779","repositories_listed":0,"syntology":null},{"url":null,"slug":"fintextqa-a-dataset-for-long-form-financial","title":"FinTextQA: A Dataset for Long-form Financial Question Answering","date":"2024-05-16","arxiv_id":"2405.09980","repositories_listed":0,"syntology":null},{"url":null,"slug":"groundedness-in-retrieval-augmented-long-form","title":"Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study","date":"2024-04-10","arxiv_id":"2404.07060","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-plan-and-generate-text-with","title":"Learning to Plan and Generate Text with Citations","date":"2024-04-04","arxiv_id":"2404.03381","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-review-fusion-in-context","title":"Multi-Review Fusion-in-Context","date":"2024-03-22","arxiv_id":"2403.15351","repositories_listed":0,"syntology":null},{"url":null,"slug":"genie-achieving-human-parity-in-content","title":"Genie: Achieving Human Parity in Content-Grounded Datasets Generation","date":"2024-01-25","arxiv_id":"2401.14367","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-form-question-answering-an-iterative","title":"Long-form Question Answering: An Iterative Planning-Retrieval-Generation Approach","date":"2023-11-15","arxiv_id":"2311.09383","repositories_listed":0,"syntology":null},{"url":null,"slug":"pinpoint-not-criticize-refining-large","title":"LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback","date":"2023-11-15","arxiv_id":"2311.09336","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-pre-trained-generative-models-for","title":"Adapting Pre-trained Generative Models for Extractive Question Answering","date":"2023-11-06","arxiv_id":"2311.02961","repositories_listed":0,"syntology":null},{"url":null,"slug":"prewome-exploiting-presuppositions-as-working","title":"PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question Answering","date":"2023-10-24","arxiv_id":"2310.16147","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-retrieval-augmentation-for-long","title":"Understanding Retrieval Augmentation for Long-Form Question Answering","date":"2023-10-18","arxiv_id":"2310.12150","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-computational-and-modeling-foundation","title":"A Novel Computational and Modeling Foundation for Automatic Coherence Assessment","date":"2023-10-01","arxiv_id":"2310.00598","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-answerability-of-llms-for-long","title":"Investigating Answerability of LLMs for Long-Form Question Answering","date":"2023-09-15","arxiv_id":"2309.08210","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-long-form-question-answering","title":"Generative Long-form Question Answering: Relevance, Faithfulness and Succinctness","date":"2022-11-15","arxiv_id":"2211.08386","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-refinement-prompts-for-closed-book-long","title":"Query Refinement Prompts for Closed-Book Long-Form Question Answering","date":"2022-10-31","arxiv_id":"2210.17525","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-exemplification-in-long-form-1","title":"Modeling Exemplification in Long-form Question Answering via Retrieval","date":"2022-05-19","arxiv_id":"2205.09278","repositories_listed":0,"syntology":null},{"url":"/paper/read-before-generate-faithful-long-form","slug":"read-before-generate-faithful-long-form","title":"Read before Generate! Faithful Long Form Question Answering with Machine Reading","date":"2022-03-01","arxiv_id":"2203.00343","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-exemplification-in-long-form","title":"Modeling Exemplification in Long-form Question Answering via Retrieval","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"new-methods-metrics-for-lfqa-tasks","title":"New Methods & Metrics for LFQA tasks","date":"2021-12-26","arxiv_id":"2112.13432","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-state-of-the-art-models-can-deal-with","title":"How State-Of-The-Art Models Can Deal With Long-Form Question Answering","date":"2020-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":8,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/task/long-form-question-answering/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":"ran","page":1,"of":1,"url":"/task/long-form-question-answering/papers/ran/1","json":"/task/long-form-question-answering/papers/ran/1.json","rows":8}],"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":"4292c6f1b55f1546e7dd7a2b1ab75ce128747208d35d1aac74b0e66458a98132","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}