{"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/instructcoder-empowering-language-models-for","title":"InstructCoder: Instruction Tuning Large Language Models for Code Editing","arxiv_id":"2310.20329","date":"2023-10-31","proceeding":null,"authors":["Kaixin Li","Qisheng Hu","Xu Zhao","Hui Chen","Yuxi Xie","Tiedong Liu","Qizhe Xie","Junxian He"],"abstract":"Code editing encompasses a variety of pragmatic tasks that developers deal with daily. Despite its relevance and practical usefulness, automatic code editing remains an underexplored area in the evolution of deep learning models, partly due to data scarcity. In this work, we explore the use of Large Language Models (LLMs) to edit code based on user instructions. Evaluated on a novel human-written execution-based benchmark dubbed EditEval, we found current models often struggle to fulfill the instructions. In light of this, we contribute InstructCoder, the first instruction-tuning dataset designed to adapt LLMs for general-purpose code editing, containing high-diversity code-editing tasks such as comment insertion, code optimization, and code refactoring. It consists of over 114,000 instruction-input-output triplets and covers multiple distinct code editing scenarios. The collection process starts with filtered commit data sourced from GitHub Python repositories as seeds. Subsequently, the dataset is systematically expanded through an iterative process, where both seed and generated tasks are used to prompt ChatGPT for more data. Our findings reveal that open-source LLMs fine-tuned on InstructCoder can significantly enhance the accuracy of code edits, exhibiting superior code-editing performance matching advanced proprietary LLMs. The datasets and the source code are publicly available at https://github.com/qishenghu/CodeInstruct.","url_abs":"https://arxiv.org/abs/2310.20329v3","url_pdf":"https://arxiv.org/pdf/2310.20329v3.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":"instructcoder-empowering-language-models-for","repo_url":"https://github.com/qishenghu/CodeInstruct","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"instructcoder-empowering-language-models-for","repo_url":"https://github.com/qishenghu/instructcoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.20329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20329"}},"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/qishenghu/instructcoder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qishenghu/CodeInstruct","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":12,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":14,"ran":13,"repositories":1},"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":"dcc63461ed8faa9d","entry":"build_program_and_tests","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"edit_eval/evaluation.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/edit_eval/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dcc63461ed8faa9d"}},{"code_sha256_prefix":"08c63a2c53e2dbbc","entry":"build_program_and_tests","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"edit_eval/validate_dataset.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/edit_eval/validate_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"08c63a2c53e2dbbc"}},{"code_sha256_prefix":"d76cd6028267121b","entry":"check_correctness","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"edit_eval/execution.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/edit_eval/execution.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d76cd6028267121b"}},{"code_sha256_prefix":"18f3d41c3a3ca45f","entry":"chunk","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"src/request_helper.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/src/request_helper.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":"18f3d41c3a3ca45f"}},{"code_sha256_prefix":"e080db2eaa81fdb3","entry":"estimate_pass_at_k","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"edit_eval/evaluation.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/edit_eval/evaluation.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e080db2eaa81fdb3"}},{"code_sha256_prefix":"7dcc28da7fcf7d21","entry":"format_filter","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"src/postprocess.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/src/postprocess.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":"7dcc28da7fcf7d21"}},{"code_sha256_prefix":"7e14c9de72446b8b","entry":"format_instance","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"src/postprocess.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/src/postprocess.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":"7e14c9de72446b8b"}},{"code_sha256_prefix":"c833dfb4c07dd2c0","entry":"get_rouge_scores","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"src/bootstrap_instructions.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/src/bootstrap_instructions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c833dfb4c07dd2c0"}},{"code_sha256_prefix":"db2f749312721290","entry":"init_logger","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"edit_eval/utils.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/edit_eval/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"db2f749312721290"}},{"code_sha256_prefix":"c0bdcc7c326efa00","entry":"load_file","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"src/generate_instance.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/src/generate_instance.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":"c0bdcc7c326efa00"}},{"code_sha256_prefix":"e84eec1ac7ee2f18","entry":"query_for_instance","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"src/generate_instance.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/src/generate_instance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e84eec1ac7ee2f18"}},{"code_sha256_prefix":"e23c1c2c0288f4d7","entry":"query_for_instruction","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"src/bootstrap_instructions.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/src/bootstrap_instructions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e23c1c2c0288f4d7"}},{"code_sha256_prefix":"9e26c9a9ed5f3dd2","entry":"query_for_scenarios","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"src/generate_scenarios.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/src/generate_scenarios.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e26c9a9ed5f3dd2"}},{"code_sha256_prefix":"e62750b3c8c67f42","entry":"sample_items","repo":"qishenghu/instructcoder","repo_kind":"listed","path":"src/bootstrap_instructions.py","file_url":"https://github.com/qishenghu/instructcoder/blob/HEAD/src/bootstrap_instructions.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e62750b3c8c67f42"}},{"code_sha256_prefix":"776a712a353130e7","entry":"read_problems","repo":"qishenghu/CodeInstruct","repo_kind":"official","path":"edit_eval/data.py","file_url":"https://github.com/qishenghu/CodeInstruct/blob/HEAD/edit_eval/data.py","link_basis":"harvester_set","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":"776a712a353130e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}