{"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/open-domain-question-answering/papers/3","list_of":"/task/open-domain-question-answering","task":"Open-Domain Question Answering","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":5,"rows_per_page":100,"rows":[201,300],"of":494,"counts":{"archive_papers_tagged":494,"with_a_code_link":238,"where_syntology_ran_a_sample":80,"not_listed_spam_title":0,"listed":494,"listed_where_code_ran":80,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":68,"every_run_a_failure_of_syntologys_instrument":12,"listed_with_a_run_with_no_instrument_failure":68,"listed_every_run_a_failure_of_syntologys_instrument":12,"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/open-domain-question-answering","prev":"/task/open-domain-question-answering/papers/2","next":"/task/open-domain-question-answering/papers/4","papers":[{"url":"/paper/a-replication-study-of-dense-passage","slug":"a-replication-study-of-dense-passage","title":"A Replication Study of Dense Passage Retriever","date":"2021-04-12","arxiv_id":"2104.05740","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/less-is-more-pre-training-a-strong-siamese","slug":"less-is-more-pre-training-a-strong-siamese","title":"Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder","date":"2021-02-18","arxiv_id":"2102.09206","repositories_listed":1,"syntology":null},{"url":"/paper/paq-65-million-probably-asked-questions-and","slug":"paq-65-million-probably-asked-questions-and","title":"PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them","date":"2021-02-13","arxiv_id":"2102.07033","repositories_listed":1,"syntology":null},{"url":"/paper/sf-qa-simple-and-fair-evaluation-library-for","slug":"sf-qa-simple-and-fair-evaluation-library-for","title":"SF-QA: Simple and Fair Evaluation Library for Open-domain Question Answering","date":"2021-01-06","arxiv_id":"2101.01910","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/a-memory-efficient-baseline-for-open-domain","slug":"a-memory-efficient-baseline-for-open-domain","title":"A Memory Efficient Baseline for Open Domain Question Answering","date":"2020-12-30","arxiv_id":"2012.15156","repositories_listed":1,"syntology":null},{"url":"/paper/unified-open-domain-question-answering-with","slug":"unified-open-domain-question-answering-with","title":"UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering","date":"2020-12-29","arxiv_id":"2012.14610","repositories_listed":1,"syntology":null},{"url":"/paper/answering-ambiguous-questions-through","slug":"answering-ambiguous-questions-through","title":"Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction","date":"2020-11-26","arxiv_id":"2011.13137","repositories_listed":1,"syntology":null},{"url":"/paper/retrieve-rerank-read-then-iterate-answering","slug":"retrieve-rerank-read-then-iterate-answering","title":"Answering Open-Domain Questions of Varying Reasoning Steps from Text","date":"2020-10-23","arxiv_id":"2010.12527","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retrieve-rerank-read-then-iterate-answering#ran","syntology_url":"https://syntology.ai/paper/2010.12527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.12527"}},"official":{"repos":["beerqa/irrr"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"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/delaying-interaction-layers-in-transformer","slug":"delaying-interaction-layers-in-transformer","title":"Delaying Interaction Layers in Transformer-based Encoders for Efficient Open Domain Question Answering","date":"2020-10-16","arxiv_id":"2010.08422","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/on-the-importance-of-adaptive-data-collection","slug":"on-the-importance-of-adaptive-data-collection","title":"On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks","date":"2020-10-10","arxiv_id":"2010.05103","repositories_listed":1,"syntology":null},{"url":"/paper/sparta-efficient-open-domain-question","slug":"sparta-efficient-open-domain-question","title":"SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval","date":"2020-09-28","arxiv_id":"2009.13013","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/question-and-answer-test-train-overlap-in","slug":"question-and-answer-test-train-overlap-in","title":"Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets","date":"2020-08-06","arxiv_id":"2008.02637","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/question-and-answer-test-train-overlap-in#ran","syntology_url":"https://syntology.ai/paper/2008.02637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02637"}},"official":{"repos":["facebookresearch/QA-Overlap"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/caire-covid-a-question-answering-and-multi","slug":"caire-covid-a-question-answering-and-multi","title":"CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management","date":"2020-05-04","arxiv_id":"2005.03975","repositories_listed":1,"syntology":null},{"url":"/paper/bert-knn-adding-a-knn-search-component-to","slug":"bert-knn-adding-a-knn-search-component-to","title":"BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA","date":"2020-05-02","arxiv_id":"2005.00766","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-dense-and-attentional-representations","slug":"sparse-dense-and-attentional-representations","title":"Sparse, Dense, and Attentional Representations for Text Retrieval","date":"2020-05-01","arxiv_id":"2005.00181","repositories_listed":1,"syntology":null},{"url":"/paper/progressively-pretrained-dense-corpus-index","slug":"progressively-pretrained-dense-corpus-index","title":"Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering","date":"2020-04-30","arxiv_id":"2005.00038","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":"/paper/language-models-as-knowledge-bases","slug":"language-models-as-knowledge-bases","title":"Language Models as Knowledge Bases?","date":"2019-09-03","arxiv_id":"1909.01066","repositories_listed":1,"syntology":null},{"url":"/paper/xqa-a-cross-lingual-open-domain-question","slug":"xqa-a-cross-lingual-open-domain-question","title":"XQA: A Cross-lingual Open-domain Question Answering Dataset","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multi-hop-paragraph-retrieval-for-open-domain","slug":"multi-hop-paragraph-retrieval-for-open-domain","title":"Multi-Hop Paragraph Retrieval for Open-Domain Question Answering","date":"2019-06-15","arxiv_id":"1906.06606","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"0 ran · 5 unverified","sample_list":"/paper/multi-hop-paragraph-retrieval-for-open-domain#ran","syntology_url":"https://syntology.ai/paper/1906.06606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.06606"}},"official":{"repos":["yairf11/MUPPET"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"url":"/paper/real-time-open-domain-question-answering-with","slug":"real-time-open-domain-question-answering-with","title":"Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index","date":"2019-06-13","arxiv_id":"1906.05807","repositories_listed":1,"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":3,"n_honours":4,"n_violates":1,"n_no_contract":9,"n_pointer_only":4,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 4 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/real-time-open-domain-question-answering-with#ran","syntology_url":"https://syntology.ai/paper/1906.05807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05807"}},"official":{"repos":["uwnlp/denspi"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-arabic-question-answering","slug":"neural-arabic-question-answering","title":"Neural Arabic Question Answering","date":"2019-06-12","arxiv_id":"1906.05394","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neural-arabic-question-answering#ran","syntology_url":"https://syntology.ai/paper/1906.05394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05394"}},"official":{"repos":["husseinmozannar/SOQAL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-step-retriever-reader-interaction-for-1","slug":"multi-step-retriever-reader-interaction-for-1","title":"Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering","date":"2019-05-14","arxiv_id":"1905.05733","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":7,"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, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-step-retriever-reader-interaction-for-1#ran","syntology_url":"https://syntology.ai/paper/1905.05733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05733"}},"official":{"repos":["rajarshd/Multi-Step-Reasoning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/evidence-sentence-extraction-for-machine","slug":"evidence-sentence-extraction-for-machine","title":"Evidence Sentence Extraction for Machine Reading Comprehension","date":"2019-02-23","arxiv_id":"1902.08852","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-open-domain-question-answering","slug":"end-to-end-open-domain-question-answering","title":"End-to-End Open-Domain Question Answering with BERTserini","date":"2019-02-05","arxiv_id":"1902.01718","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-open-domain-question-answering#ran","syntology_url":"https://syntology.ai/paper/1902.01718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01718"}},"official":{"repos":["rsvp-ai/bertserini"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-pair-text-representations-for-answer","slug":"cross-pair-text-representations-for-answer","title":"Cross-Pair Text Representations for Answer Sentence Selection","date":"2018-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ranking-paragraphs-for-improving-answer","slug":"ranking-paragraphs-for-improving-answer","title":"Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering","date":"2018-10-01","arxiv_id":"1810.00494","repositories_listed":1,"syntology":null},{"url":"/paper/open-domain-event-detection-using-distant","slug":"open-domain-event-detection-using-distant","title":"Open-Domain Event Detection using Distant Supervision","date":"2018-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/denoising-distantly-supervised-open-domain","slug":"denoising-distantly-supervised-open-domain","title":"Denoising Distantly Supervised Open-Domain Question Answering","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-question-focused-multi-factor-attention","slug":"a-question-focused-multi-factor-attention","title":"A Question-Focused Multi-Factor Attention Network for Question Answering","date":"2018-01-25","arxiv_id":"1801.08290","repositories_listed":1,"syntology":null},{"url":"/paper/evidence-aggregation-for-answer-re-ranking-in","slug":"evidence-aggregation-for-answer-re-ranking-in","title":"Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering","date":"2017-11-14","arxiv_id":"1711.05116","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":2,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evidence-aggregation-for-answer-re-ranking-in#ran","syntology_url":"https://syntology.ai/paper/1711.05116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.05116"}},"official":{"repos":["shuohangwang/mprc"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/r3-reinforced-reader-ranker-for-open-domain","slug":"r3-reinforced-reader-ranker-for-open-domain","title":"R$^3$: Reinforced Reader-Ranker for Open-Domain Question Answering","date":"2017-08-31","arxiv_id":"1709.00023","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-parsing-via-staged-query-graph","slug":"semantic-parsing-via-staged-query-graph","title":"Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base","date":"2015-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"efficient-context-selection-for-long-context","title":"Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-$k$","date":"2025-06-10","arxiv_id":"2506.08479","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-llm-multiple-roles-a-unified-retrieval","title":"Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization","date":"2025-05-21","arxiv_id":"2505.15444","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-knowledge-utilization-mechanisms-in","title":"Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation","date":"2025-05-17","arxiv_id":"2505.11995","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-retrieval-augmented-generation","title":"Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task","date":"2025-04-04","arxiv_id":"2504.03616","repositories_listed":0,"syntology":null},{"url":null,"slug":"corag-collaborative-retrieval-augmented","title":"CoRAG: Collaborative Retrieval-Augmented Generation","date":"2025-04-02","arxiv_id":"2504.01883","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-aware-iterative-retrieval-for-multi","title":"Knowledge-Aware Iterative Retrieval for Multi-Agent Systems","date":"2025-03-17","arxiv_id":"2503.13275","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-open-domain-question-answering","title":"Optimizing open-domain question answering with graph-based retrieval augmented generation","date":"2025-03-04","arxiv_id":"2503.02922","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01606","title":"Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering","date":"2025-03-03","arxiv_id":"2503.01606","repositories_listed":0,"syntology":null},{"url":null,"slug":"webfaq-a-multilingual-collection-of-natural-q","title":"WebFAQ: A Multilingual Collection of Natural Q&A Datasets for Dense Retrieval","date":"2025-02-28","arxiv_id":"2502.20936","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-retrieval-to-generation-comparing","title":"From Retrieval to Generation: Comparing Different Approaches","date":"2025-02-27","arxiv_id":"2502.20245","repositories_listed":0,"syntology":null},{"url":null,"slug":"roserag-robust-retrieval-augmented-generation","title":"RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization","date":"2025-02-16","arxiv_id":"2502.10993","repositories_listed":0,"syntology":null},{"url":null,"slug":"asrank-zero-shot-re-ranking-with-answer-scent","title":"ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrieval","date":"2025-01-25","arxiv_id":"2501.15245","repositories_listed":0,"syntology":null},{"url":null,"slug":"passage-segmentation-of-documents-for","title":"Passage Segmentation of Documents for Extractive Question Answering","date":"2025-01-17","arxiv_id":"2501.09940","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-key-value-cache-fusion-for-position","title":"Parallel Key-Value Cache Fusion for Position Invariant RAG","date":"2025-01-13","arxiv_id":"2501.07523","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-generated-and-retrieved-knowledge","title":"Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation","date":"2024-12-25","arxiv_id":"2412.18800","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-manufacturing-scale-up-from","title":"Accelerating Manufacturing Scale-Up from Material Discovery Using Agentic Web Navigation and Retrieval-Augmented AI for Process Engineering Schematics Design","date":"2024-12-08","arxiv_id":"2412.05937","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynrank-improving-passage-retrieval-with","title":"DynRank: Improving Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification","date":"2024-11-30","arxiv_id":"2412.00600","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-llms-understand-ambiguity-in-text-a-case","title":"Do LLMs Understand Ambiguity in Text? A Case Study in Open-world Question Answering","date":"2024-11-19","arxiv_id":"2411.12395","repositories_listed":0,"syntology":null},{"url":null,"slug":"invar-rag-invariant-llm-aligned-retrieval-for","title":"Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation","date":"2024-11-11","arxiv_id":"2411.07021","repositories_listed":0,"syntology":null},{"url":null,"slug":"judgerank-leveraging-large-language-models","title":"JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking","date":"2024-10-31","arxiv_id":"2411.00142","repositories_listed":0,"syntology":null},{"url":null,"slug":"improve-dense-passage-retrieval-with","title":"Improve Dense Passage Retrieval with Entailment Tuning","date":"2024-10-21","arxiv_id":"2410.15801","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-large-language-model-attribution","title":"Advancing Large Language Model Attribution through Self-Improving","date":"2024-10-17","arxiv_id":"2410.13298","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-domain-question-answering-with","title":"Open Domain Question Answering with Conflicting Contexts","date":"2024-10-16","arxiv_id":"2410.12311","repositories_listed":0,"syntology":null},{"url":null,"slug":"banglaquad-a-bengali-open-domain-question","title":"BanglaQuAD: A Bengali Open-domain Question Answering Dataset","date":"2024-10-14","arxiv_id":"2410.10229","repositories_listed":0,"syntology":null},{"url":null,"slug":"lore-logit-ranked-retriever-ensemble-for","title":"LoRE: Logit-Ranked Retriever Ensemble for Enhancing Open-Domain Question Answering","date":"2024-10-13","arxiv_id":"2410.10042","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multimodal-dense-retrieval-approach-for","title":"A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering","date":"2024-09-20","arxiv_id":"2409.13483","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-statistical-framework-for-data-dependent","title":"A Statistical Framework for Data-dependent Retrieval-Augmented Models","date":"2024-08-27","arxiv_id":"2408.15399","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-human-level-understanding-of-complex","title":"Towards Human-Level Understanding of Complex Process Engineering Schematics: A Pedagogical, Introspective Multi-Agent Framework for Open-Domain Question Answering","date":"2024-08-24","arxiv_id":"2409.00082","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-robustness-of-retrieval-augmented","title":"Enhancing Robustness of Retrieval-Augmented Language Models with In-Context Learning","date":"2024-08-08","arxiv_id":"2408.04414","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01084","title":"Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts","date":"2024-08-02","arxiv_id":"2408.01084","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-evaluation-a-comprehensive","title":"Towards Robust Evaluation: A Comprehensive Taxonomy of Datasets and Metrics for Open Domain Question Answering in the Era of Large Language Models","date":"2024-06-19","arxiv_id":"2406.13232","repositories_listed":0,"syntology":null},{"url":null,"slug":"calm-contrasting-large-and-small-language","title":"CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation","date":"2024-06-08","arxiv_id":"2406.05365","repositories_listed":0,"syntology":null},{"url":null,"slug":"spaghetti-open-domain-question-answering-from","title":"SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing","date":"2024-06-01","arxiv_id":"2406.00562","repositories_listed":0,"syntology":null},{"url":null,"slug":"conv-coa-improving-open-domain-question","title":"Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action","date":"2024-05-28","arxiv_id":"2405.17822","repositories_listed":0,"syntology":null},{"url":null,"slug":"agrame-any-granularity-ranking-with-multi","title":"AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings","date":"2024-05-23","arxiv_id":"2405.15028","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-can-self-correct-with","title":"Large Language Models Can Self-Correct with Key Condition Verification","date":"2024-05-23","arxiv_id":"2405.14092","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-long-text-understanding-with","title":"Improving Long Text Understanding with Knowledge Distilled from Summarization Model","date":"2024-05-08","arxiv_id":"2405.04955","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-long-context-for-enhancing-rag","title":"Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation","date":"2024-05-06","arxiv_id":"2405.03085","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-rag-end-to-end-retrieval-augmented","title":"Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization","date":"2024-05-05","arxiv_id":"2405.02816","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-table-retrieval-a-solved-problem-join","title":"Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval","date":"2024-04-15","arxiv_id":"2404.09889","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-better-generalization-in-open-domain","title":"Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization","date":"2024-04-02","arxiv_id":"2404.01652","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-quality-matters-in-training-fusion-in","title":"Context Quality Matters in Training Fusion-in-Decoder for Extractive Open-Domain Question Answering","date":"2024-03-21","arxiv_id":"2403.14197","repositories_listed":0,"syntology":null},{"url":null,"slug":"fit-rag-black-box-rag-with-factual","title":"FIT-RAG: Black-Box RAG with Factual Information and Token Reduction","date":"2024-03-21","arxiv_id":"2403.14374","repositories_listed":0,"syntology":null},{"url":null,"slug":"answerability-in-retrieval-augmented-open","title":"Answerability in Retrieval-Augmented Open-Domain Question Answering","date":"2024-03-03","arxiv_id":"2403.01461","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-question-answer-generation-for-long","title":"Automatic Question-Answer Generation for Long-Tail Knowledge","date":"2024-03-03","arxiv_id":"2403.01382","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-in-conversation-solving-subjective","title":"Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models","date":"2024-02-27","arxiv_id":"2402.17226","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-dc-when-to-retrieve-and-when-to-generate","title":"Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions","date":"2024-02-21","arxiv_id":"2402.13514","repositories_listed":0,"syntology":null},{"url":null,"slug":"blendfilter-advancing-retrieval-augmented","title":"BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering","date":"2024-02-16","arxiv_id":"2402.11129","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dataset-of-open-domain-question-answering","title":"A Dataset of Open-Domain Question Answering with Multiple-Span Answers","date":"2024-02-15","arxiv_id":"2402.09923","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-chain-of-thought-is-as-strong-as-its","title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","date":"2024-02-01","arxiv_id":"2402.00559","repositories_listed":0,"syntology":null},{"url":null,"slug":"cfmatch-aligning-automated-answer-equivalence","title":"CFMatch: Aligning Automated Answer Equivalence Evaluation with Expert Judgments For Open-Domain Question Answering","date":"2024-01-24","arxiv_id":"2401.13170","repositories_listed":0,"syntology":null},{"url":null,"slug":"narrowing-the-knowledge-evaluation-gap-open","title":"Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers","date":"2024-01-09","arxiv_id":"2401.04695","repositories_listed":0,"syntology":null},{"url":null,"slug":"entity-augmented-code-generation","title":"Dynamic Retrieval-Augmented Generation","date":"2023-12-14","arxiv_id":"2312.08976","repositories_listed":0,"syntology":null},{"url":null,"slug":"hint-enhanced-in-context-learning-wakes-large","title":"Hint-enhanced In-Context Learning wakes Large Language Models up for knowledge-intensive tasks","date":"2023-11-03","arxiv_id":"2311.01949","repositories_listed":0,"syntology":null},{"url":null,"slug":"divknowqa-assessing-the-reasoning-ability-of","title":"DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text","date":"2023-10-31","arxiv_id":"2310.20170","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-zero-shot-reader-by-reducing","title":"Improving Zero-shot Reader by Reducing Distractions from Irrelevant Documents in Open-Domain Question Answering","date":"2023-10-26","arxiv_id":"2310.17490","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-feedback-knowledge-retrieval-for-task","title":"Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems","date":"2023-10-23","arxiv_id":"2310.14528","repositories_listed":0,"syntology":null},{"url":null,"slug":"strong-and-efficient-baselines-for-open","title":"Strong and Efficient Baselines for Open Domain Conversational Question Answering","date":"2023-10-23","arxiv_id":"2310.14708","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-hallucination-assessment-for","title":"ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks","date":"2023-10-19","arxiv_id":"2310.12516","repositories_listed":0,"syntology":null},{"url":"/paper/ra-dit-retrieval-augmented-dual-instruction","slug":"ra-dit-retrieval-augmented-dual-instruction","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","date":"2023-10-02","arxiv_id":"2310.01352","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieving-supporting-evidence-for-generative","title":"Retrieving Supporting Evidence for Generative Question Answering","date":"2023-09-20","arxiv_id":"2309.11392","repositories_listed":0,"syntology":null},{"url":null,"slug":"silverretriever-advancing-neural-passage","title":"Silver Retriever: Advancing Neural Passage Retrieval for Polish Question Answering","date":"2023-09-15","arxiv_id":"2309.08469","repositories_listed":0,"syntology":null}],"record_sha256":"bb435a4ff1a2791c424cae6a2f3ff1d7cb8c9bba5a69a15441c5b14f7bc04e1c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}