{"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/exploring-format-consistency-for-instruction","title":"Exploring Format Consistency for Instruction Tuning","arxiv_id":"2307.15504","date":"2023-07-28","proceeding":null,"authors":["Shihao Liang","Runchu Tian","Kunlun Zhu","Yujia Qin","Huadong Wang","Xin Cong","Zhiyuan Liu","Xiaojiang Liu","Maosong Sun"],"abstract":"Instruction tuning has emerged as a promising approach to enhancing large language models in following human instructions. It is shown that increasing the diversity and number of instructions in the training data can consistently enhance generalization performance, which facilitates a recent endeavor to collect various instructions and integrate existing instruction tuning datasets into larger collections. However, different users have their unique ways of expressing instructions, and there often exist variations across different datasets in the instruction styles and formats, i.e., format inconsistency. In this work, we propose a framework named Unified Instruction Tuning (UIT), which calls OpenAI APIs for automatic format transfer among different instruction tuning datasets such as PromptSource, FLAN and CrossFit. With the framework, we (1) demonstrate the necessity of maintaining format consistency in instruction tuning; (2) improve the generalization performance on unseen instructions on T5-LM-xl; (3) provide a novel perplexity-based denoising method to reduce the noise of automatic format transfer to make the UIT framework more practical and a smaller offline model based on GPT-J that achieves comparable format transfer capability to OpenAI APIs to reduce costs in practice. Further analysis regarding variations of targeted formats and other effects is intended.","url_abs":"https://arxiv.org/abs/2307.15504v2","url_pdf":"https://arxiv.org/pdf/2307.15504v2.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":"exploring-format-consistency-for-instruction","repo_url":"https://github.com/thunlp/unifiedinstructiontuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.15504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15504"}},"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/unifiedinstructiontuning","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"935ca5f6d5581e30","entry":"add_custom_argument","repo":"thunlp/unifiedinstructiontuning","repo_kind":"official","path":"model_center/arguments.py","file_url":"https://github.com/thunlp/unifiedinstructiontuning/blob/HEAD/model_center/arguments.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":"935ca5f6d5581e30"}},{"code_sha256_prefix":"c8e969fe51c6f843","entry":"add_model_config_args","repo":"thunlp/unifiedinstructiontuning","repo_kind":"official","path":"model_center/arguments.py","file_url":"https://github.com/thunlp/unifiedinstructiontuning/blob/HEAD/model_center/arguments.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":"c8e969fe51c6f843"}},{"code_sha256_prefix":"2610bd6913783d7c","entry":"build_dataset","repo":"thunlp/unifiedinstructiontuning","repo_kind":"official","path":"model_center/dataset/distributed_dataset.py","file_url":"https://github.com/thunlp/unifiedinstructiontuning/blob/HEAD/model_center/dataset/distributed_dataset.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":"2610bd6913783d7c"}},{"code_sha256_prefix":"13534729932a1182","entry":"add_training_args","repo":"thunlp/unifiedinstructiontuning","repo_kind":"official","path":"model_center/arguments.py","file_url":"https://github.com/thunlp/unifiedinstructiontuning/blob/HEAD/model_center/arguments.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":"13534729932a1182"}},{"code_sha256_prefix":"18d94355ea8f1c39","entry":"code","repo":"thunlp/unifiedinstructiontuning","repo_kind":"official","path":"model_center/dataset/distributed_indexed.py","file_url":"https://github.com/thunlp/unifiedinstructiontuning/blob/HEAD/model_center/dataset/distributed_indexed.py","link_basis":"harvester_set","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":"18d94355ea8f1c39"}},{"code_sha256_prefix":"bdf28f9492a770dc","entry":"data_file_path","repo":"thunlp/unifiedinstructiontuning","repo_kind":"official","path":"model_center/dataset/distributed_indexed.py","file_url":"https://github.com/thunlp/unifiedinstructiontuning/blob/HEAD/model_center/dataset/distributed_indexed.py","link_basis":"harvester_set","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":"bdf28f9492a770dc"}},{"code_sha256_prefix":"8b1a74a6db32c163","entry":"index_file_path","repo":"thunlp/unifiedinstructiontuning","repo_kind":"official","path":"model_center/dataset/distributed_indexed.py","file_url":"https://github.com/thunlp/unifiedinstructiontuning/blob/HEAD/model_center/dataset/distributed_indexed.py","link_basis":"harvester_set","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":"8b1a74a6db32c163"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}