{"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/chain-of-thought-unfaithfulness-as-disguised","title":"Chain-of-Thought Unfaithfulness as Disguised Accuracy","arxiv_id":"2402.14897","date":"2024-02-22","proceeding":null,"authors":["Oliver Bentham","Nathan Stringham","Ana Marasović"],"abstract":"Understanding the extent to which Chain-of-Thought (CoT) generations align with a large language model's (LLM) internal computations is critical for deciding whether to trust an LLM's output. As a proxy for CoT faithfulness, Lanham et al. (2023) propose a metric that measures a model's dependence on its CoT for producing an answer. Within a single family of proprietary models, they find that LLMs exhibit a scaling-then-inverse-scaling relationship between model size and their measure of faithfulness, and that a 13 billion parameter model exhibits increased faithfulness compared to models ranging from 810 million to 175 billion parameters in size. We evaluate whether these results generalize as a property of all LLMs. We replicate the experimental setup in their section focused on scaling experiments with three different families of models and, under specific conditions, successfully reproduce the scaling trends for CoT faithfulness they report. However, after normalizing the metric to account for a model's bias toward certain answer choices, unfaithfulness drops significantly for smaller less-capable models. This normalized faithfulness metric is also strongly correlated ($R^2$=0.74) with accuracy, raising doubts about its validity for evaluating faithfulness.","url_abs":"https://arxiv.org/abs/2402.14897v3","url_pdf":"https://arxiv.org/pdf/2402.14897v3.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":"chain-of-thought-unfaithfulness-as-disguised","repo_url":"https://github.com/utahnlp/cot_disguised_accuracy","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.14897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14897"}},"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/utahnlp/cot_disguised_accuracy","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"3ece7e535f584aec","entry":"construct_addition_prompt","repo":"utahnlp/cot_disguised_accuracy","repo_kind":"official","path":"src/prompt.py","file_url":"https://github.com/utahnlp/cot_disguised_accuracy/blob/HEAD/src/prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3ece7e535f584aec"}},{"code_sha256_prefix":"253e0688e81299b8","entry":"construct_mcq_prompt","repo":"utahnlp/cot_disguised_accuracy","repo_kind":"official","path":"src/prompt.py","file_url":"https://github.com/utahnlp/cot_disguised_accuracy/blob/HEAD/src/prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"253e0688e81299b8"}},{"code_sha256_prefix":"0fb12b2e89c536c8","entry":"shuffle_choice_order","repo":"utahnlp/cot_disguised_accuracy","repo_kind":"official","path":"src/mcq.py","file_url":"https://github.com/utahnlp/cot_disguised_accuracy/blob/HEAD/src/mcq.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0fb12b2e89c536c8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}