{"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/variational-open-domain-question-answering","title":"Variational Open-Domain Question Answering","arxiv_id":"2210.06345","date":"2022-09-23","proceeding":null,"authors":["Valentin Liévin","Andreas Geert Motzfeldt","Ida Riis Jensen","Ole Winther"],"abstract":"Retrieval-augmented models have proven to be effective in natural language processing tasks, yet there remains a lack of research on their optimization using variational inference. We introduce the Variational Open-Domain (VOD) framework for end-to-end training and evaluation of retrieval-augmented models, focusing on open-domain question answering and language modelling. The VOD objective, a self-normalized estimate of the R\\'enyi variational bound, approximates the task marginal likelihood and is evaluated under samples drawn from an auxiliary sampling distribution (cached retriever and/or approximate posterior). It remains tractable, even for retriever distributions defined on large corpora. We demonstrate VOD's versatility by training reader-retriever BERT-sized models on multiple-choice medical exam questions. On the MedMCQA dataset, we outperform the domain-tuned Med-PaLM by +5.3% despite using 2.500$\\times$ fewer parameters. Our retrieval-augmented BioLinkBERT model scored 62.9% on the MedMCQA and 55.0% on the MedQA-USMLE. Last, we show the effectiveness of our learned retriever component in the context of medical semantic search.","url_abs":"https://arxiv.org/abs/2210.06345v2","url_pdf":"https://arxiv.org/pdf/2210.06345v2.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":"variational-open-domain-question-answering","repo_url":"https://github.com/findzebra/fz-openqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"variational-open-domain-question-answering","repo_url":"https://github.com/VodLM/vod","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":null,"task_name":"MedQA"},{"task_slug":"multiple-choice-qa","task_name":"Multiple Choice Question Answering (MCQA)"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"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"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[{"slug":"fz-queries","name":"FZ queries","full_name":"FindZebra queries"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-21","task":"Multiple Choice Question Answering (MCQA)","dataset":"MedMCQA","model":"VOD (BioLinkBERT)","rank_in_archive_order":4,"of":22,"metrics":{"Dev Set (Acc-%)":"0.583","Test Set (Acc-%)":"0.629"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-medqa-usmle","task":"Question Answering","dataset":"MedQA","model":"VOD (BioLinkBERT)","rank_in_archive_order":15,"of":27,"metrics":{"Accuracy":"55.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.06345","atlas_url":"https://app.syntology.ai/?focus=2210.06345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06345"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/VodLM/vod","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/findzebra/fz-openqa","reach":{"status":"ok"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"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":0,"samples":[{"code_sha256_prefix":"0c2a3c350e11f679","entry":"combine_datasets","repo":"VodLM/vod","repo_kind":"official","path":"src/vod_datasets/postprocessing.py","file_url":"https://github.com/VodLM/vod/blob/HEAD/src/vod_datasets/postprocessing.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0c2a3c350e11f679"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}