{"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/failures-pave-the-way-enhancing-large","title":"Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation","arxiv_id":"2310.15746","date":"2023-10-24","proceeding":null,"authors":["Zeyuan Yang","Peng Li","Yang Liu"],"abstract":"Large Language Models (LLMs) have showcased impressive performance. However, due to their inability to capture relationships among samples, these frozen LLMs inevitably keep repeating similar mistakes. In this work, we propose our Tuning-free Rule Accumulation (TRAN) framework, which guides LLMs in improving their performance by learning from previous mistakes. Considering data arrives sequentially, LLMs gradually accumulate rules from incorrect cases, forming a rule collection. These rules are then utilized by the LLMs to avoid making similar mistakes when processing subsequent inputs. Moreover, the rules remain independent of the primary prompts, seamlessly complementing prompt design strategies. Experimentally, we show that TRAN improves over recent baselines by a large margin.","url_abs":"https://arxiv.org/abs/2310.15746v1","url_pdf":"https://arxiv.org/pdf/2310.15746v1.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":"failures-pave-the-way-enhancing-large","repo_url":"https://github.com/thunlp-mt/tran","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.15746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15746"}},"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/thunlp-mt/tran","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":"6bb6ac903885edef","entry":"compare_rules","repo":"thunlp-mt/tran","repo_kind":"official","path":"utils.py","file_url":"https://github.com/thunlp-mt/tran/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6bb6ac903885edef"}},{"code_sha256_prefix":"5daf7e15c3044058","entry":"get_valid_rules","repo":"thunlp-mt/tran","repo_kind":"official","path":"utils.py","file_url":"https://github.com/thunlp-mt/tran/blob/HEAD/utils.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5daf7e15c3044058"}},{"code_sha256_prefix":"c0a3e2ca942b21f5","entry":"RuleBook","repo":"thunlp-mt/tran","repo_kind":"official","path":"utils.py","file_url":"https://github.com/thunlp-mt/tran/blob/HEAD/utils.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":"c0a3e2ca942b21f5"}},{"code_sha256_prefix":"3ea8126d2bbe4d60","entry":"post_message","repo":"thunlp-mt/tran","repo_kind":"official","path":"utils.py","file_url":"https://github.com/thunlp-mt/tran/blob/HEAD/utils.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":"3ea8126d2bbe4d60"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}