{"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-consistency-improves-chain-of-thought","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","arxiv_id":"2203.11171","date":"2022-03-21","proceeding":null,"authors":["Xuezhi Wang","Jason Wei","Dale Schuurmans","Quoc Le","Ed Chi","Sharan Narang","Aakanksha Chowdhery","Denny Zhou"],"abstract":"Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy decoding used in chain-of-thought prompting. It first samples a diverse set of reasoning paths instead of only taking the greedy one, and then selects the most consistent answer by marginalizing out the sampled reasoning paths. Self-consistency leverages the intuition that a complex reasoning problem typically admits multiple different ways of thinking leading to its unique correct answer. Our extensive empirical evaluation shows that self-consistency boosts the performance of chain-of-thought prompting with a striking margin on a range of popular arithmetic and commonsense reasoning benchmarks, including GSM8K (+17.9%), SVAMP (+11.0%), AQuA (+12.2%), StrategyQA (+6.4%) and ARC-challenge (+3.9%).","url_abs":"https://arxiv.org/abs/2203.11171v4","url_pdf":"https://arxiv.org/pdf/2203.11171v4.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":"self-consistency-improves-chain-of-thought","repo_url":"https://github.com/hughbzhang/o1_inference_scaling_laws","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"self-consistency-improves-chain-of-thought","repo_url":"https://github.com/codelion/optillm/blob/main/optillm/self_consistency.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"self-consistency-improves-chain-of-thought","repo_url":"https://github.com/lastmile-ai/aiconfig/tree/main/cookbooks/Multi-LLM-Consistency","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"arc","task_name":"ARC"},{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"math","task_name":"Math"},{"task_slug":"strategyqa","task_name":"StrategyQA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"PaLM 540B maj1@40 (8-shot)","rank_in_archive_order":87,"of":164,"metrics":{"Accuracy":"74.4","Parameters (Billion)":"540"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.11171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11171"}},"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":"deterministic:regex_extraction","url":"https://github.com/google-research/google-research","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hughbzhang/o1_inference_scaling_laws","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lastmile-ai/aiconfig/tree/main/cookbooks/Multi-LLM-Consistency","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/codelion/optillm/blob/main/optillm/self_consistency.py","reach":null}],"summary":{"ran":1},"by_repo_kind":{"listed":{"samples":1,"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":"8d36e472d3ec3597","entry":"AdvancedSelfConsistency","repo":"codelion/optillm","repo_kind":"listed","path":"optillm/self_consistency.py","file_url":"https://github.com/codelion/optillm/blob/HEAD/optillm/self_consistency.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8d36e472d3ec3597"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}