{"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/self-critique-and-refinement-for-faithful","title":"Self-Critique and Refinement for Faithful Natural Language Explanations","arxiv_id":"2505.22823","date":"2025-05-28","proceeding":null,"authors":["Yingming Wang","Pepa Atanasova"],"abstract":"With the rapid development of large language models (LLMs), natural language explanations (NLEs) have become increasingly important for understanding model predictions. However, these explanations often fail to faithfully represent the model's actual reasoning process. While existing work has demonstrated that LLMs can self-critique and refine their initial outputs for various tasks, this capability remains unexplored for improving explanation faithfulness. To address this gap, we introduce Self-critique and Refinement for Natural Language Explanations (SR-NLE), a framework that enables models to improve the faithfulness of their own explanations -- specifically, post-hoc NLEs -- through an iterative critique and refinement process without external supervision. Our framework leverages different feedback mechanisms to guide the refinement process, including natural language self-feedback and, notably, a novel feedback approach based on feature attribution that highlights important input words. Our experiments across three datasets and four state-of-the-art LLMs demonstrate that SR-NLE significantly reduces unfaithfulness rates, with our best method achieving an average unfaithfulness rate of 36.02%, compared to 54.81% for baseline -- an absolute reduction of 18.79%. These findings reveal that the investigated LLMs can indeed refine their explanations to better reflect their actual reasoning process, requiring only appropriate guidance through feedback without additional training or fine-tuning.","url_abs":"https://arxiv.org/abs/2505.22823v1","url_pdf":"https://arxiv.org/pdf/2505.22823v1.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":[],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.22823","atlas_url":"https://app.syntology.ai/?focus=2505.22823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.22823"}},"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/ymwangv/SR-NLE","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"found_in_text":{"samples":8,"ran":3,"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":8,"samples":[{"code_sha256_prefix":"d16d614f67054efa","entry":"fill_prompt_template","repo":"ymwangv/SR-NLE","repo_kind":"found_in_text","path":"src/modules/refinement_generator.py","file_url":"https://github.com/ymwangv/SR-NLE/blob/HEAD/src/modules/refinement_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d16d614f67054efa"}},{"code_sha256_prefix":"93b536159e7d6e60","entry":"format_options","repo":"ymwangv/SR-NLE","repo_kind":"found_in_text","path":"src/modules/refinement_generator.py","file_url":"https://github.com/ymwangv/SR-NLE/blob/HEAD/src/modules/refinement_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"93b536159e7d6e60"}},{"code_sha256_prefix":"0011e2b3c7468a9f","entry":"parse","repo":"ymwangv/SR-NLE","repo_kind":"found_in_text","path":"src/modules/refinement_generator.py","file_url":"https://github.com/ymwangv/SR-NLE/blob/HEAD/src/modules/refinement_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0011e2b3c7468a9f"}},{"code_sha256_prefix":"7d4964fef332d343","entry":"GeneralGenerator","repo":"ymwangv/SR-NLE","repo_kind":"found_in_text","path":"src/modules/refinement_generator.py","file_url":"https://github.com/ymwangv/SR-NLE/blob/HEAD/src/modules/refinement_generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d4964fef332d343"}},{"code_sha256_prefix":"94757c101dbb4570","entry":"GenerationModel","repo":"ymwangv/SR-NLE","repo_kind":"found_in_text","path":"src/modules/refinement_generator.py","file_url":"https://github.com/ymwangv/SR-NLE/blob/HEAD/src/modules/refinement_generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"94757c101dbb4570"}},{"code_sha256_prefix":"12443c71b583199b","entry":"RefinementGenerator","repo":"ymwangv/SR-NLE","repo_kind":"found_in_text","path":"src/modules/refinement_generator.py","file_url":"https://github.com/ymwangv/SR-NLE/blob/HEAD/src/modules/refinement_generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"12443c71b583199b"}},{"code_sha256_prefix":"03a86ea75bc5be98","entry":"apply_voting","repo":"ymwangv/SR-NLE","repo_kind":"found_in_text","path":"src/modules/refinement_generator.py","file_url":"https://github.com/ymwangv/SR-NLE/blob/HEAD/src/modules/refinement_generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"03a86ea75bc5be98"}},{"code_sha256_prefix":"d78b1f961441eb3c","entry":"get_prompt_template","repo":"ymwangv/SR-NLE","repo_kind":"found_in_text","path":"src/modules/refinement_generator.py","file_url":"https://github.com/ymwangv/SR-NLE/blob/HEAD/src/modules/refinement_generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d78b1f961441eb3c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}