{"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/escape-sky-high-cost-early-stopping-self","title":"Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning","arxiv_id":"2401.10480","date":"2024-01-19","proceeding":null,"authors":["Yiwei Li","Peiwen Yuan","Shaoxiong Feng","Boyuan Pan","Xinglin Wang","Bin Sun","HeDa Wang","Kan Li"],"abstract":"Self-consistency (SC) has been a widely used decoding strategy for chain-of-thought reasoning. Despite bringing significant performance improvements across a variety of multi-step reasoning tasks, it is a high-cost method that requires multiple sampling with the preset size. In this paper, we propose a simple and scalable sampling process, \\textbf{E}arly-Stopping \\textbf{S}elf-\\textbf{C}onsistency (ESC), to greatly reduce the cost of SC without sacrificing performance. On this basis, one control scheme for ESC is further derivated to dynamically choose the performance-cost balance for different tasks and models. To demonstrate ESC's effectiveness, we conducted extensive experiments on three popular categories of reasoning tasks: arithmetic, commonsense and symbolic reasoning over language models with varying scales. The empirical results show that ESC reduces the average number of sampling of chain-of-thought reasoning by a significant margin on six benchmarks, including MATH (-33.8%), GSM8K (-80.1%), StrategyQA (-76.8%), CommonsenseQA (-78.5%), Coin Flip (-84.2%) and Last Letters (-67.4%), while attaining comparable performances.","url_abs":"https://arxiv.org/abs/2401.10480v1","url_pdf":"https://arxiv.org/pdf/2401.10480v1.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":"escape-sky-high-cost-early-stopping-self","repo_url":"https://github.com/yiwei98/esc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"},{"task_slug":"strategyqa","task_name":"StrategyQA"}],"methods":[{"method_slug":"flip","method_name":"FLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.10480","atlas_url":"https://app.syntology.ai/?focus=2401.10480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10480"}},"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/Yiwei98/ESC","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yiwei98/esc","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"6bca6b3b72790204","entry":"cal_n","repo":"Yiwei98/ESC","repo_kind":"official","path":"control_scheme.py","file_url":"https://github.com/Yiwei98/ESC/blob/HEAD/control_scheme.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6bca6b3b72790204"}},{"code_sha256_prefix":"85b14139a0b81918","entry":"entropy","repo":"Yiwei98/ESC","repo_kind":"official","path":"consistency_coin.py","file_url":"https://github.com/Yiwei98/ESC/blob/HEAD/consistency_coin.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"85b14139a0b81918"}},{"code_sha256_prefix":"d95f990735eba145","entry":"extract_answer","repo":"Yiwei98/ESC","repo_kind":"official","path":"consistency_gsm8k.py","file_url":"https://github.com/Yiwei98/ESC/blob/HEAD/consistency_gsm8k.py","link_basis":"harvester_set","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":"d95f990735eba145"}},{"code_sha256_prefix":"6ec18dd15818d034","entry":"extract_answer","repo":"Yiwei98/ESC","repo_kind":"official","path":"consistency_coin.py","file_url":"https://github.com/Yiwei98/ESC/blob/HEAD/consistency_coin.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ec18dd15818d034"}},{"code_sha256_prefix":"b550af4a369be974","entry":"extract_answer","repo":"Yiwei98/ESC","repo_kind":"official","path":"consistency_csqa.py","file_url":"https://github.com/Yiwei98/ESC/blob/HEAD/consistency_csqa.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b550af4a369be974"}},{"code_sha256_prefix":"691cea85ad41fe0e","entry":"extract_answer","repo":"Yiwei98/ESC","repo_kind":"official","path":"consistency_last.py","file_url":"https://github.com/Yiwei98/ESC/blob/HEAD/consistency_last.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"691cea85ad41fe0e"}},{"code_sha256_prefix":"3a7fa93c63c0feb2","entry":"find_answer","repo":"Yiwei98/ESC","repo_kind":"official","path":"consistency_coin.py","file_url":"https://github.com/Yiwei98/ESC/blob/HEAD/consistency_coin.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a7fa93c63c0feb2"}},{"code_sha256_prefix":"0743ac11d38bfc42","entry":"cal_n","repo":"yiwei98/esc","repo_kind":"official","path":"control_scheme.py","file_url":"https://github.com/yiwei98/esc/blob/HEAD/control_scheme.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0743ac11d38bfc42"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}