{"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/llms-with-chain-of-thought-are-non-causal","title":"How Likely Do LLMs with CoT Mimic Human Reasoning?","arxiv_id":"2402.16048","date":"2024-02-25","proceeding":null,"authors":["Guangsheng Bao","Hongbo Zhang","Cunxiang Wang","Linyi Yang","Yue Zhang"],"abstract":"Chain-of-thought emerges as a promising technique for eliciting reasoning capabilities from Large Language Models (LLMs). However, it does not always improve task performance or accurately represent reasoning processes, leaving unresolved questions about its usage. In this paper, we diagnose the underlying mechanism by comparing the reasoning process of LLMs with humans, using causal analysis to understand the relationships between the problem instruction, reasoning, and the answer in LLMs. Our empirical study reveals that LLMs often deviate from the ideal causal chain, resulting in spurious correlations and potential consistency errors (inconsistent reasoning and answers). We also examine various factors influencing the causal structure, finding that in-context learning with examples strengthens it, while post-training techniques like supervised fine-tuning and reinforcement learning on human feedback weaken it. To our surprise, the causal structure cannot be strengthened by enlarging the model size only, urging research on new techniques. We hope that this preliminary study will shed light on understanding and improving the reasoning process in LLM.","url_abs":"https://arxiv.org/abs/2402.16048v3","url_pdf":"https://arxiv.org/pdf/2402.16048v3.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":"llms-with-chain-of-thought-are-non-causal","repo_url":"https://github.com/stevenzhb/cot_causal_analysis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.16048","atlas_url":"https://app.syntology.ai/?focus=2402.16048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16048"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stevenzhb/cot_causal_analysis","reach":null}],"summary":{"ran_draft_wrong":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":"4882d7701eefb906","entry":"add_bias_sentence","repo":"stevenzhb/cot_causal_analysis","repo_kind":"official","path":"scripts/api_run.py","file_url":"https://github.com/stevenzhb/cot_causal_analysis/blob/HEAD/scripts/api_run.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4882d7701eefb906"}},{"code_sha256_prefix":"7c56d76aa689e7f0","entry":"load_prompt","repo":"stevenzhb/cot_causal_analysis","repo_kind":"official","path":"scripts/api_run.py","file_url":"https://github.com/stevenzhb/cot_causal_analysis/blob/HEAD/scripts/api_run.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":"7c56d76aa689e7f0"}},{"code_sha256_prefix":"12c9534e0a9e4b9f","entry":"make_n_shot","repo":"stevenzhb/cot_causal_analysis","repo_kind":"official","path":"scripts/api_run.py","file_url":"https://github.com/stevenzhb/cot_causal_analysis/blob/HEAD/scripts/api_run.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":"12c9534e0a9e4b9f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}