{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/retrieve-rerank-read-then-iterate-answering","title":"Answering Open-Domain Questions of Varying Reasoning Steps from Text","arxiv_id":"2010.12527","date":"2020-10-23","proceeding":"EMNLP 2021 11","authors":["Peng Qi","Haejun Lee","Oghenetegiri \"TG\" Sido","Christopher D. Manning"],"abstract":"We develop a unified system to answer directly from text open-domain questions that may require a varying number of retrieval steps. We employ a single multi-task transformer model to perform all the necessary subtasks -- retrieving supporting facts, reranking them, and predicting the answer from all retrieved documents -- in an iterative fashion. We avoid crucial assumptions of previous work that do not transfer well to real-world settings, including exploiting knowledge of the fixed number of retrieval steps required to answer each question or using structured metadata like knowledge bases or web links that have limited availability. Instead, we design a system that can answer open-domain questions on any text collection without prior knowledge of reasoning complexity. To emulate this setting, we construct a new benchmark, called BeerQA, by combining existing one- and two-step datasets with a new collection of 530 questions that require three Wikipedia pages to answer, unifying Wikipedia corpora versions in the process. We show that our model demonstrates competitive performance on both existing benchmarks and this new benchmark. We make the new benchmark available at https://beerqa.github.io/.","url_abs":"https://arxiv.org/abs/2010.12527v4","url_pdf":"https://arxiv.org/pdf/2010.12527v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"retrieve-rerank-read-then-iterate-answering","repo_url":"https://github.com/beerqa/irrr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reranking","task_name":"Reranking"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-hotpotqa","task":"Question Answering","dataset":"HotpotQA","model":"IRRR+","rank_in_archive_order":9,"of":72,"metrics":{"ANS-EM":"0.663","ANS-F1":"0.791","JOINT-EM":"0.428","JOINT-F1":"0.696","SUP-EM":"0.569","SUP-F1":"0.832"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-hotpotqa","task":"Question Answering","dataset":"HotpotQA","model":"IRRR","rank_in_archive_order":11,"of":72,"metrics":{"ANS-EM":"0.657","ANS-F1":"0.782","JOINT-EM":"0.421","JOINT-F1":"0.686","SUP-EM":"0.559","SUP-F1":"0.821"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.12527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.12527"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/beerqa/irrr","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_violates":1,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"f6c275d6a18330a9","entry":"exact_match_score","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f6c275d6a18330a9"}},{"code_sha256_prefix":"2112c433b9c6d343","entry":"f1_score","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"2112c433b9c6d343"}},{"code_sha256_prefix":"c6a80c065d2e4851","entry":"normalize_answer","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"c6a80c065d2e4851"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}