{"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/f1-is-not-enough-models-and-evaluation","title":"F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering","arxiv_id":"2010.06283","date":"2020-10-13","proceeding":"EMNLP 2020 11","authors":["Hendrik Schuff","Heike Adel","Ngoc Thang Vu"],"abstract":"Explainable question answering systems predict an answer together with an explanation showing why the answer has been selected. The goal is to enable users to assess the correctness of the system and understand its reasoning process. However, we show that current models and evaluation settings have shortcomings regarding the coupling of answer and explanation which might cause serious issues in user experience. As a remedy, we propose a hierarchical model and a new regularization term to strengthen the answer-explanation coupling as well as two evaluation scores to quantify the coupling. We conduct experiments on the HOTPOTQA benchmark data set and perform a user study. The user study shows that our models increase the ability of the users to judge the correctness of the system and that scores like F1 are not enough to estimate the usefulness of a model in a practical setting with human users. Our scores are better aligned with user experience, making them promising candidates for model selection.","url_abs":"https://arxiv.org/abs/2010.06283v1","url_pdf":"https://arxiv.org/pdf/2010.06283v1.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":"f1-is-not-enough-models-and-evaluation","repo_url":"https://github.com/boschresearch/f1-is-not-enough","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"model-selection","task_name":"Model Selection"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2010.06283","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06283"}},"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/boschresearch/f1-is-not-enough","reach":null}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"d6e262d22194245b","entry":"BiAttention","repo":"boschresearch/f1-is-not-enough","repo_kind":"official","path":"code/select_and_forget.py","file_url":"https://github.com/boschresearch/f1-is-not-enough/blob/HEAD/code/select_and_forget.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d6e262d22194245b"}},{"code_sha256_prefix":"1f0ec64ef973f938","entry":"EncoderRNN","repo":"boschresearch/f1-is-not-enough","repo_kind":"official","path":"code/select_and_forget.py","file_url":"https://github.com/boschresearch/f1-is-not-enough/blob/HEAD/code/select_and_forget.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1f0ec64ef973f938"}},{"code_sha256_prefix":"a1f9ac55219bbb35","entry":"LockedDropout","repo":"boschresearch/f1-is-not-enough","repo_kind":"official","path":"code/select_and_forget.py","file_url":"https://github.com/boschresearch/f1-is-not-enough/blob/HEAD/code/select_and_forget.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a1f9ac55219bbb35"}},{"code_sha256_prefix":"e9b1301589108aa0","entry":"SelectAndForgetModel","repo":"boschresearch/f1-is-not-enough","repo_kind":"official","path":"code/select_and_forget.py","file_url":"https://github.com/boschresearch/f1-is-not-enough/blob/HEAD/code/select_and_forget.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e9b1301589108aa0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}