{"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/distilling-knowledge-from-reader-to-retriever-1","title":"Distilling Knowledge from Reader to Retriever for Question Answering","arxiv_id":"2012.04584","date":"2020-12-08","proceeding":"ICLR 2021 1","authors":["Gautier Izacard","Edouard Grave"],"abstract":"The task of information retrieval is an important component of many natural language processing systems, such as open domain question answering. While traditional methods were based on hand-crafted features, continuous representations based on neural networks recently obtained competitive results. A challenge of using such methods is to obtain supervised data to train the retriever model, corresponding to pairs of query and support documents. In this paper, we propose a technique to learn retriever models for downstream tasks, inspired by knowledge distillation, and which does not require annotated pairs of query and documents. Our approach leverages attention scores of a reader model, used to solve the task based on retrieved documents, to obtain synthetic labels for the retriever. We evaluate our method on question answering, obtaining state-of-the-art results.","url_abs":"https://arxiv.org/abs/2012.04584v2","url_pdf":"https://arxiv.org/pdf/2012.04584v2.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":"distilling-knowledge-from-reader-to-retriever-1","repo_url":"https://github.com/facebookresearch/FiD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"distilling-knowledge-from-reader-to-retriever-1","repo_url":"https://github.com/FenQQQ/Fusion-in-decoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"distilling-knowledge-from-reader-to-retriever-1","repo_url":"https://github.com/hackerchenzhuo/LaKo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distilling-knowledge-from-reader-to-retriever-1","repo_url":"https://github.com/lucidrains/marge-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-narrativeqa","task":"Question Answering","dataset":"NarrativeQA","model":"FiD+Distil","rank_in_archive_order":9,"of":10,"metrics":{"BLEU-1":"35.3","BLEU-4":"7.5","METEOR":"11.1","Rouge-L":"32"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-triviaqa","task":"Question Answering","dataset":"TriviaQA","model":"FiD+Distil","rank_in_archive_order":27,"of":56,"metrics":{"EM":"72.1"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.04584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.04584"}},"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/FenQQQ/Fusion-in-decoder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hackerchenzhuo/LaKo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/FiD","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/marge-pytorch","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"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":1,"samples":[{"code_sha256_prefix":"bc7a7a194c238080","entry":"add_embeddings","repo":"FenQQQ/Fusion-in-decoder","repo_kind":"listed","path":"passage_retrieval.py","file_url":"https://github.com/FenQQQ/Fusion-in-decoder/blob/HEAD/passage_retrieval.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bc7a7a194c238080"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}