{"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/towards-consistent-natural-language","title":"Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning","arxiv_id":"2401.13986","date":"2024-01-25","proceeding":null,"authors":["Yanda Chen","Chandan Singh","Xiaodong Liu","Simiao Zuo","Bin Yu","He He","Jianfeng Gao"],"abstract":"Large language models (LLMs) often generate convincing, fluent explanations. However, different from humans, they often generate inconsistent explanations on different inputs. For example, an LLM may generate the explanation \"all birds can fly\" when answering the question \"Can sparrows fly?\" but meanwhile answer \"no\" to the related question \"Can penguins fly?\". Explanations should be consistent across related examples so that they allow a human to simulate the LLM's decision process on multiple examples. We propose explanation-consistency finetuning (EC-finetuning), a method that adapts LLMs to generate more consistent natural-language explanations on related examples. EC-finetuning involves finetuning LLMs on synthetic data that is carefully constructed to contain consistent explanations. Across a variety of question-answering datasets in various domains, EC-finetuning yields a 10.0% relative explanation consistency improvement on four finetuning datasets, and generalizes to seven out-of-distribution datasets not seen during finetuning (+4.5% relative). Code is available at https://github.com/yandachen/explanation-consistency-finetuning .","url_abs":"https://arxiv.org/abs/2401.13986v1","url_pdf":"https://arxiv.org/pdf/2401.13986v1.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":"towards-consistent-natural-language","repo_url":"https://github.com/yandachen/explanation-consistency-finetuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.13986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.13986"}},"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/yandachen/explanation-consistency-finetuning","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"36182f61757cdc95","entry":"calculate_consistency_example","repo":"yandachen/explanation-consistency-finetuning","repo_kind":"official","path":"src/score_consistency.py","file_url":"https://github.com/yandachen/explanation-consistency-finetuning/blob/HEAD/src/score_consistency.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"36182f61757cdc95"}},{"code_sha256_prefix":"1a39aa47d58da56a","entry":"extract_answer_from_output","repo":"yandachen/explanation-consistency-finetuning","repo_kind":"official","path":"src/expl_generation.py","file_url":"https://github.com/yandachen/explanation-consistency-finetuning/blob/HEAD/src/expl_generation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a39aa47d58da56a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}