{"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/dissociation-of-faithful-and-unfaithful","title":"Dissociation of Faithful and Unfaithful Reasoning in LLMs","arxiv_id":"2405.15092","date":"2024-05-23","proceeding":null,"authors":["Evelyn Yee","Alice Li","Chenyu Tang","Yeon Ho Jung","Ramamohan Paturi","Leon Bergen"],"abstract":"Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how LLMs recover from errors in Chain of Thought. Through analysis of error recovery behaviors, we find evidence for unfaithfulness in Chain of Thought, which occurs when models arrive at the correct answer despite invalid reasoning text. We identify factors that shift LLM recovery behavior: LLMs recover more frequently from obvious errors and in contexts that provide more evidence for the correct answer. Critically, these factors have divergent effects on faithful and unfaithful recoveries. Our results indicate that there are distinct mechanisms driving faithful and unfaithful error recoveries. Selective targeting of these mechanisms may be able to drive down the rate of unfaithful reasoning and improve model interpretability.","url_abs":"https://arxiv.org/abs/2405.15092v2","url_pdf":"https://arxiv.org/pdf/2405.15092v2.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":"dissociation-of-faithful-and-unfaithful","repo_url":"https://github.com/coterrorrecovery/coterrorrecovery","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.15092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15092"}},"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/coterrorrecovery/coterrorrecovery","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":"8d49a8d0a4ba0d54","entry":"typo","repo":"coterrorrecovery/coterrorrecovery","repo_kind":"official","path":"code/number_intervention.py","file_url":"https://github.com/coterrorrecovery/coterrorrecovery/blob/HEAD/code/number_intervention.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d49a8d0a4ba0d54"}},{"code_sha256_prefix":"203a4c074526078a","entry":"intervention","repo":"coterrorrecovery/coterrorrecovery","repo_kind":"official","path":"code/letter_intervention.py","file_url":"https://github.com/coterrorrecovery/coterrorrecovery/blob/HEAD/code/letter_intervention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"203a4c074526078a"}},{"code_sha256_prefix":"5429cf9009c180da","entry":"perturbation_num","repo":"coterrorrecovery/coterrorrecovery","repo_kind":"official","path":"code/letter_intervention.py","file_url":"https://github.com/coterrorrecovery/coterrorrecovery/blob/HEAD/code/letter_intervention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5429cf9009c180da"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}