{"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/inversecoder-unleashing-the-power-of","title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct","arxiv_id":"2407.05700","date":"2024-07-08","proceeding":null,"authors":["Yutong Wu","Di Huang","Wenxuan Shi","Wei Wang","Lingzhe Gao","Shihao Liu","Ziyuan Nan","Kaizhao Yuan","Rui Zhang","Xishan Zhang","Zidong Du","Qi Guo","Yewen Pu","Dawei Yin","Xing Hu","Yunji Chen"],"abstract":"Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it is possible to use a fine-tuned open-source model to generate additional data to augment its instruction-tuning dataset. We make two observations: (1) A code snippet can serve as the response to different instructions. (2) Instruction-tuned code LLMs perform better at translating code into instructions than the reverse. Based on these observations, we propose Inverse-Instruct, a data augmentation technique that uses a fine-tuned LLM to generate additional instructions of code responses from its own training dataset. The additional instruction-response pairs are added to the original dataset, and a stronger code LLM can be obtained by fine-tuning on the augmented dataset. We empirically validate Inverse-Instruct on a range of open-source code models (e.g. CodeLlama-Python and DeepSeek-Coder) and benchmarks (e.g., HumanEval(+), MBPP(+), DS-1000 and MultiPL-E), showing it consistently improves the base models.","url_abs":"https://arxiv.org/abs/2407.05700v2","url_pdf":"https://arxiv.org/pdf/2407.05700v2.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":"inversecoder-unleashing-the-power-of","repo_url":"https://github.com/wyt2000/InverseCoder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"code-summarization-1","task_name":"Code Summarization"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"humaneval","task_name":"HumanEval"},{"task_slug":"text-to-code-generation","task_name":"Text-to-Code Generation"},{"task_slug":null,"task_name":"mbpp"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.05700","atlas_url":"https://app.syntology.ai/?focus=2407.05700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05700"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wyt2000/InverseCoder","reach":{"status":"ok"}}],"summary":{"ran":11},"by_repo_kind":{"official":{"samples":11,"ran":11,"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":11,"samples":[{"code_sha256_prefix":"4ba4d218cc21b7c3","entry":"extract_code","repo":"wyt2000/InverseCoder","repo_kind":"official","path":"src/InstGen/sample_vllm.py","file_url":"https://github.com/wyt2000/InverseCoder/blob/HEAD/src/InstGen/sample_vllm.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":"4ba4d218cc21b7c3"}},{"code_sha256_prefix":"2e57c27d5464d633","entry":"extract_code","repo":"wyt2000/InverseCoder","repo_kind":"official","path":"src/InstGen/sample_vllm_parallel.py","file_url":"https://github.com/wyt2000/InverseCoder/blob/HEAD/src/InstGen/sample_vllm_parallel.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":"2e57c27d5464d633"}},{"code_sha256_prefix":"e9e120f8e994775b","entry":"generate_one_prompt","repo":"wyt2000/InverseCoder","repo_kind":"official","path":"src/InstGen/sample_vllm.py","file_url":"https://github.com/wyt2000/InverseCoder/blob/HEAD/src/InstGen/sample_vllm.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":"e9e120f8e994775b"}},{"code_sha256_prefix":"e95fcf0bebb8c47b","entry":"generate_one_prompt","repo":"wyt2000/InverseCoder","repo_kind":"official","path":"src/InstGen/sample_vllm_parallel.py","file_url":"https://github.com/wyt2000/InverseCoder/blob/HEAD/src/InstGen/sample_vllm_parallel.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":"e95fcf0bebb8c47b"}},{"code_sha256_prefix":"105ce67ee1510057","entry":"generate_one_prompt","repo":"wyt2000/InverseCoder","repo_kind":"official","path":"src/InstGen/sample_vllm_parallel_completion.py","file_url":"https://github.com/wyt2000/InverseCoder/blob/HEAD/src/InstGen/sample_vllm_parallel_completion.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":"105ce67ee1510057"}},{"code_sha256_prefix":"6e56413da9949793","entry":"generate_one_prompt","repo":"wyt2000/InverseCoder","repo_kind":"official","path":"src/InstGen/sample_vllm_parallel_completion_deepseek.py","file_url":"https://github.com/wyt2000/InverseCoder/blob/HEAD/src/InstGen/sample_vllm_parallel_completion_deepseek.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":"6e56413da9949793"}},{"code_sha256_prefix":"59ecbfd3747bcfa8","entry":"generate_one_prompt","repo":"wyt2000/InverseCoder","repo_kind":"official","path":"src/InstGen/sample_vllm_parallel_description_prompt.py","file_url":"https://github.com/wyt2000/InverseCoder/blob/HEAD/src/InstGen/sample_vllm_parallel_description_prompt.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":"59ecbfd3747bcfa8"}},{"code_sha256_prefix":"b5bde94f66a46787","entry":"generate_prompts","repo":"wyt2000/InverseCoder","repo_kind":"official","path":"src/InstGen/sample_vllm.py","file_url":"https://github.com/wyt2000/InverseCoder/blob/HEAD/src/InstGen/sample_vllm.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":"b5bde94f66a46787"}},{"code_sha256_prefix":"bcd581a56aa8495e","entry":"generate_prompts","repo":"wyt2000/InverseCoder","repo_kind":"official","path":"src/InstGen/sample_vllm_parallel.py","file_url":"https://github.com/wyt2000/InverseCoder/blob/HEAD/src/InstGen/sample_vllm_parallel.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":"bcd581a56aa8495e"}},{"code_sha256_prefix":"dd2e6518d155b0b2","entry":"generate_prompts","repo":"wyt2000/InverseCoder","repo_kind":"official","path":"src/InstGen/sample_vllm_parallel_description_prompt.py","file_url":"https://github.com/wyt2000/InverseCoder/blob/HEAD/src/InstGen/sample_vllm_parallel_description_prompt.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":"dd2e6518d155b0b2"}},{"code_sha256_prefix":"49a6d5371d92242a","entry":"get_language","repo":"wyt2000/InverseCoder","repo_kind":"official","path":"src/InstGen/sample_vllm_parallel_completion.py","file_url":"https://github.com/wyt2000/InverseCoder/blob/HEAD/src/InstGen/sample_vllm_parallel_completion.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":"49a6d5371d92242a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}