{"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/scar-efficient-instruction-tuning-for-large","title":"SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking","arxiv_id":"2406.10882","date":"2024-06-16","proceeding":null,"authors":["Zhuang Li","Yuncheng Hua","Thuy-Trang Vu","Haolan Zhan","Lizhen Qu","Gholamreza Haffari"],"abstract":"Recent studies emphasize that manually ensuring a consistent response style and maintaining high data quality in training sets can significantly improve the performance of fine-tuned Large Language Models (LLMs) while reducing the number of training examples needed. However, the precise definition of style and the relationship between style, data quality, and LLM performance remains unclear. This research identifies two key stylistic elements in responses: linguistic form and instructional surprisal. We find that, among training data of comparable quality, higher consistency in these response elements leads to better LLM performance. Inspired by this, we introduce Style Consistency-Aware Response Ranking (SCAR), which automatically prioritizes instruction-response pairs in the training set based on their response stylistic consistency. By selecting the most style-consistent examples, sometimes as few as 0.7% of the full dataset, the fine-tuned LLMs can match or even surpass the performance of models trained on the entire dataset in coding and open-ended question-answering benchmarks. Code and data are available at https://github.com/zhuang-li/SCAR .","url_abs":"https://arxiv.org/abs/2406.10882v7","url_pdf":"https://arxiv.org/pdf/2406.10882v7.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":"scar-efficient-instruction-tuning-for-large","repo_url":"https://github.com/zhuang-li/scar","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.10882","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10882"}},"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/zhuang-li/scar","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2,"ran_fixture":1,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":"446c2e26ddd3e712","entry":"StyleRankerConfig","repo":"zhuang-li/scar","repo_kind":"official","path":"style_ranker/rank.py","file_url":"https://github.com/zhuang-li/scar/blob/HEAD/style_ranker/rank.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"446c2e26ddd3e712"}},{"code_sha256_prefix":"872a7d219ac4f5ba","entry":"filter_pairs","repo":"zhuang-li/scar","repo_kind":"official","path":"style_ranker/rank.py","file_url":"https://github.com/zhuang-li/scar/blob/HEAD/style_ranker/rank.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":"872a7d219ac4f5ba"}},{"code_sha256_prefix":"8650457881a66b1a","entry":"max_pooling","repo":"zhuang-li/scar","repo_kind":"official","path":"style_ranker/rank.py","file_url":"https://github.com/zhuang-li/scar/blob/HEAD/style_ranker/rank.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8650457881a66b1a"}},{"code_sha256_prefix":"476d87d414281b45","entry":"rank_pairs","repo":"zhuang-li/scar","repo_kind":"official","path":"style_ranker/rank.py","file_url":"https://github.com/zhuang-li/scar/blob/HEAD/style_ranker/rank.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"476d87d414281b45"}},{"code_sha256_prefix":"f1eaa3d559d1bf6a","entry":"score_pairs","repo":"zhuang-li/scar","repo_kind":"official","path":"style_ranker/rank.py","file_url":"https://github.com/zhuang-li/scar/blob/HEAD/style_ranker/rank.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f1eaa3d559d1bf6a"}},{"code_sha256_prefix":"c9f0da8f635d38af","entry":"StyleRanker","repo":"zhuang-li/scar","repo_kind":"official","path":"style_ranker/rank.py","file_url":"https://github.com/zhuang-li/scar/blob/HEAD/style_ranker/rank.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c9f0da8f635d38af"}},{"code_sha256_prefix":"e8c1e5d48ca54047","entry":"load_ranker","repo":"zhuang-li/scar","repo_kind":"official","path":"style_ranker/rank.py","file_url":"https://github.com/zhuang-li/scar/blob/HEAD/style_ranker/rank.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e8c1e5d48ca54047"}},{"code_sha256_prefix":"965d3a99371ffb57","entry":"rank_and_filter","repo":"zhuang-li/scar","repo_kind":"official","path":"style_ranker/rank.py","file_url":"https://github.com/zhuang-li/scar/blob/HEAD/style_ranker/rank.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"965d3a99371ffb57"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}