Elamur Research⌕
☰
home / papers / 2024 / SelfCodeAlign: Self-Alignment for Code Generation

SelfCodeAlign: Self-Alignment for Code Generation

Paper · 2024 · Yuxiang Wei, Federico Cassano, Jiawei Liu et al.

Summary

Instruction-tuning code LLMs usually depends on expensive human-written data or on outputs from proprietary models, whose terms may forbid such use. SelfCodeAlign removes both dependencies. A base model produces all of its own training data, and every step is open and permissively licensed. The pipeline works in four steps:

  • It starts from Python seed functions taken from The Stack V1.
  • The base model lists the programming concepts each seed uses.
  • It then writes new tasks from those concepts, with randomly assigned difficulty and category.
  • For each task it drafts several solutions with accompanying tests, which run in a sandbox. Only one passing solution per task is kept.

Applied to CodeQwen1.5-7B, the pipeline yielded 74k instruction-response pairs. The tuned model outperforms CodeLlama-70B-Instruct on HumanEval+ and beats the OctoPack-tuned variant on every benchmark tested. The method works for models from 3B to 33B. It also outperforms GPT-3.5-based distillation datasets and direct GPT-4o distillation. This shows that strong code assistants can be built without a stronger teacher model. The approach also produced StarCoder2-Instruct.

Key points

  • Seed set: about 250k Python functions selected from roughly 5M documented functions in The Stack V1. Filtering used the Pyright type checker, removal of benchmark items, documentation-quality checks and near-duplicate removal.
  • Instruction generation (Self-OSS-Instruct) relies on 21 hand-crafted few-shot examples and a separate concept-extraction stage.
  • SelfCodeAlign-CQ-7B reaches 67.1 pass@1 on HumanEval+. This is 21.4 points above base CodeQwen1.5-7B and 16.5 points above CodeQwen1.5-7B-OctoPack.
  • On equal-sized 74k subsets, the results compare as follows:
    • OSS-Instruct: 61.6
    • Evol-Instruct: 59.1
    • GPT-4o response distillation: 65.9
    • SelfCodeAlign: 67.1
  • Base models learned better from their own data distribution than from a shifted teacher distribution. Stated limitations include a context window of about 3000 tokens, unused negative samples, and possibly faulty self-generated tests.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksInformation Systems · 1,437 worksComputer Science Applications · 102 works

🧭 Topics 1Research subjects and languages the work is about.Code & programming languages · 129 works

Cite

Cite as Yuxiang Wei, Federico Cassano, Jiawei Liu, Yifeng Ding, Naman Jain, Zachary Mueller, Harm de Vries, Leandro von Werra, Arjun Guha and Lingming Zhang. 2024. SelfCodeAlign: Self-Alignment for Code Generation. arXiv:2410.24198.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2410.24198 · arXiv 2410.24198

@misc{wei2024selfcodealign,
  title = {{SelfCodeAlign: Self-Alignment for Code Generation}},
  author = {Yuxiang Wei, Federico Cassano, Jiawei Liu, Yifeng Ding, Naman Jain, Zachary Mueller, Harm {de Vries}, Leandro {von Werra}, Arjun Guha and Lingming Zhang},
  year = {2024},
  doi = {10.48550/arxiv.2410.24198},
  eprint = {2410.24198},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2410.24198}
}

References

84 references, 27 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. W. U. Ahmad, M. G. R. Tushar, S. Chakraborty, and K.-W. Chang. Avatar: A parallel corpus for java-python program translation. arXiv preprint arXiv:2108.11590, 2021. find
  2. Anthropic. Terms of service, 7 2023. Accessed: August 17, 2023. find
  3. J. Austin, A. Odena, M. I. Nye, M. Bosma, H. Michalewski, D. Dohan, E. Jiang, C. J. Cai, M. Terry, Q. V. Le, and C. Sutton. Program synthesis with large language models. CoRR, abs/2108.07732, 2021.
  4. Y. Bai, X. Lv, J. Zhang, Y. He, J. Qi, L. Hou, J. Tang, Y. Dong, and J. Li. Longalign: A recipe for long context alignment of large language models, 2024.
  5. F. Cassano, J. Gouwar, F. Lucchetti, C. Schlesinger, A. Freeman, C. J. Anderson, M. Q. Feldman, M. Greenberg, A. Jangda, and A. Guha. Knowledge transfer from high-resource to low-resource programming languages for Code LLMs, 2024. find
  6. F. Cassano, L. Li, A. Sethi, N. Shinn, A. Brennan-Jones, A. Lozhkov, C. J. Anderson, and A. Guha. Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions. In The First International Workshop on Large Language Model for Code, 2024. find
  7. S. Chaudhary. Code alpaca: An instruction-following llama model for code generation. https://github.com/sahil280114/codealpaca, 2023. ↗
  8. M. Chen, J. Tworek, H. Jun, Q. Yuan, H. P. de Oliveira Pinto, J. Kaplan, H. Edwards, Y. Burda, N. Joseph, G. Brockman, A. Ray, R. Puri, G. Krueger, M. Petrov, H. Khlaaf, G. Sastry, P. Mishkin, B. Chan, S. Gray, N. Ryder, M. Pavlov, A. Power, L. Kaiser, M. Bavarian, C. Winter, P. Tillet, F. P. Such,… — Evaluating Large Language Models Trained on Code
  9. C. Cummins, V. Seeker, D. Grubisic, M. Elhoushi, Y. Liang, B. Roziere, J. Gehring, F. Gloeckle, K. Hazelwood, G. Synnaeve, et al. Large language models for compiler optimization. arXiv preprint arXiv:2309.07062, 2023. find
  10. Y. Deng, C. S. Xia, H. Peng, C. Yang, and L. Zhang. Large language models are zero-shot fuzzers: Fuzzing deep-learning libraries via large language models, 2023. find
  11. Y. Ding, H. Ding, S. Wang, Q. Sun, V. Kumar, and Z. Wang. Horizon-length prediction: Advancing fill-in-the-middle capabilities for code generation with lookahead planning. arXiv preprint arXiv:2410.03103, 2024. — [arXiv:2410.03103](https://arxiv.org/abs/2410.03103) find
  12. Y. Ding, J. Liu, Y. Wei, and L. Zhang. XFT: Unlocking the power of code instruction tuning by simply merging upcycled mixture-of-experts. In L.-W. Ku, A. Martins, and V. Srikumar, editors, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)… find
  13. X. Du, M. Liu, K. Wang, H. Wang, J. Liu, Y. Chen, J. Feng, C. Sha, X. Peng, and Y. Lou. Classeval: A manually-crafted benchmark for evaluating llms on class-level code generation. arXiv preprint arXiv:2308.01861, 2023. — [arXiv:2308.01861](https://arxiv.org/abs/2308.01861) find
  14. A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, A. Schelten, A. Yang, A. Fan, A. Goyal, A. Hartshorn, A. Yang, A. Mitra, A. Sravankumar, A. Korenev, A. Hinsvark, A. Rao, A. Zhang, A. Rodriguez, A. Gregerson, A. Spataru, B. Roziere, B. Biron, B. Tang, B. Chern, C. Cauche… — The Llama 3 Herd of Models
  15. J. Gehring, K. Zheng, J. Copet, V. Mella, T. Cohen, and G. Synnaeve. Rlef: Grounding code llms in execution feedback with reinforcement learning, 2024.
  16. A. Gomez. Introducing command r+: A scalable llm built for business, April 4 2024. Accessed: 2024-05-22. find
  17. Google. Generative ai terms of service, 8 2023. Accessed: August 17, 2023. find
  18. S. Gunasekar, Y. Zhang, J. Aneja, C. C. T. Mendes, A. D. Giorno, S. Gopi, M. Javaheripi, P. Kauffmann, G. de Rosa, O. Saarikivi, A. Salim, S. Shah, H. S. Behl, X. Wang, S. Bubeck, R. Eldan, A. T. Kalai, Y. T. Lee, and Y. Li. Textbooks are all you need, 2023. find
  19. D. Guo, Q. Zhu, D. Yang, Z. Xie, K. Dong, W. Zhang, G. Chen, X. Bi, Y. Wu, Y. K. Li, F. Luo, Y. Xiong, and W. Liang. Deepseek-coder: When the large language model meets programming – the rise of code intelligence, 2024. find
  20. P. Haluptzok, M. Bowers, and A. T. Kalai. Language models can teach themselves to program better. In The Eleventh International Conference on Learning Representations, 2023. find
  21. N. Jain, K. Han, A. Gu, W.-D. Li, F. Yan, T. Zhang, S. Wang, A. Solar-Lezama, K. Sen, and I. Stoica. Livecodebench: Holistic and contamination free evaluation of large language models for code. arXiv preprint arXiv:2403.07974, 2024.
  22. A. Q. Jiang, A. Sablayrolles, A. Mensch, C. Bamford, D. S. Chaplot, D. de las Casas, F. Bressand, G. Lengyel, G. Lample, L. Saulnier, L. R. Lavaud, M.-A. Lachaux, P. Stock, T. L. Scao, T. Lavril, T. Wang, T. Lacroix, and W. E. Sayed. Mistral 7b, 2023. find
  23. A. Q. Jiang, A. Sablayrolles, A. Roux, A. Mensch, B. Savary, C. Bamford, D. S. Chaplot, D. de las Casas, E. B. Hanna, F. Bressand, G. Lengyel, G. Bour, G. Lample, L. R. Lavaud, L. Saulnier, M.-A. Lachaux, P. Stock, S. Subramanian, S. Yang, S. Antoniak, T. L. Scao, T. Gervet, T. Lavril, T. Wang, T. L… find
  24. N. Jiang, K. Liu, T. Lutellier, and L. Tan. Impact of code language models on automated program repair. In 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), pages 1430–1442. IEEE, 2023. find
  25. C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and K. Narasimhan. Swe-bench: Can language models resolve real-world github issues? arXiv preprint arXiv:2310.06770, 2023.
  26. C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press, and K. Narasimhan. Swe-bench: Can language models resolve real-world github issues?, 2023.
  27. M. Jin, S. Shahriar, M. Tufano, X. Shi, S. Lu, N. Sundaresan, and A. Svyatkovskiy. Inferfix: End-to-end program repair with llms. In Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pages 1646–1656, 2023. find
  28. D. Kocetkov, R. Li, L. B. Allal, J. Li, C. Mou, C. M. Ferrandis, Y. Jernite, M. Mitchell, S. Hughes, T. Wolf, D. Bahdanau, L. von Werra, and H. de Vries. The stack: 3 tb of permissively licensed source code, 2022. find
  29. A. Köpf, Y. Kilcher, D. von Rütte, S. Anagnostidis, Z. R. Tam, K. Stevens, A. Barhoum, D. M. Nguyen, O. Stanley, R. Nagyfi, S. ES, S. Suri, D. A. Glushkov, A. V. Dantuluri, A. Maguire, C. Schuhmann, H. Nguyen, and A. J. Mattick. Openassistant conversations - democratizing large language model alignm… — OpenAssistant Conversations — Democratizing Large Language Model Alignment
  30. Y. Lai, C. Li, Y. Wang, T. Zhang, R. Zhong, L. Zettlemoyer, S. W. tau Yih, D. Fried, S. Wang, and T. Yu. Ds-1000: A natural and reliable benchmark for data science code generation, 2022. find
  31. H. Le, Y. Wang, A. D. Gotmare, S. Savarese, and S. Hoi. CodeRL: Mastering code generation through pretrained models and deep reinforcement learning. In A. H. Oh, A. Agarwal, D. Belgrave, and K. Cho, editors, Advances in Neural Information Processing Systems, 2022.
  32. C. Lemieux, J. P. Inala, S. K. Lahiri, and S. Sen. Codamosa: Escaping coverage plateaus in test generation with pre-trained large language models. In 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), pages 919–931. IEEE, 2023. find
  33. R. Li, L. B. Allal, Y. Zi, N. Muennighoff, D. Kocetkov, C. Mou, M. Marone, C. Akiki, J. Li, J. Chim, Q. Liu, E. Zheltonozhskii, T. Y. Zhuo, T. Wang, O. Dehaene, M. Davaadorj, J. Lamy-Poirier, J. Monteiro, O. Shliazhko, N. Gontier, N. Meade, A. Zebaze, M.-H. Yee, L. K. Umapathi, J. Zhu, B. Lipkin, M.… find
  34. X. Li, P. Yu, C. Zhou, T. Schick, O. Levy, L. Zettlemoyer, J. E. Weston, and M. Lewis. Self-alignment with instruction backtranslation. In The Twelfth International Conference on Learning Representations, 2024.
  35. X. Li, P. Yu, C. Zhou, T. Schick, O. Levy, L. Zettlemoyer, J. E. Weston, and M. Lewis. Self-alignment with instruction backtranslation. In The Twelfth International Conference on Learning Representations, 2024.
  36. J. Liu, T. Nguyen, M. Shang, H. Ding, X. Li, Y. Yu, V. Kumar, and Z. Wang. Learning code preference via synthetic evolution. arXiv preprint arXiv:2410.03837, 2024. — [arXiv:2410.03837](https://arxiv.org/abs/2410.03837) find
  37. J. Liu, K. Wang, Y. Chen, X. Peng, Z. Chen, L. Zhang, and Y. Lou. Large language model-based agents for software engineering: A survey. arXiv preprint arXiv:2409.02977, 2024. — [arXiv:2409.02977](https://arxiv.org/abs/2409.02977) find
  38. J. Liu, C. S. Xia, Y. Wang, and L. Zhang. Is your code generated by chatGPT really correct? rigorous evaluation of large language models for code generation. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  39. J. Liu, S. Xie, J. Wang, Y. Wei, Y. Ding, and L. Zhang. Evaluating language models for efficient code generation. In First Conference on Language Modeling, 2024. find
  40. A. Lozhkov, R. Li, L. B. Allal, F. Cassano, J. Lamy-Poirier, N. Tazi, A. Tang, D. Pykhtar, J. Liu, Y. Wei, et al. Starcoder 2 and the stack v2: The next generation. arXiv preprint arXiv:2402.19173, 2024. find
  41. Z. Luo, C. Xu, P. Zhao, Q. Sun, X. Geng, W. Hu, C. Tao, J. Ma, Q. Lin, and D. Jiang. Wizardcoder: Empowering code large language models with evol-instruct, 2023. find
  42. R. Meng, M. Mirchev, M. Böhme, and A. Roychoudhury. Large language model guided protocol fuzzing. In Proceedings of the 31st Annual Network and Distributed System Security Symposium (NDSS), 2024. find
  43. N. Muennighoff, Q. Liu, A. Zebaze, Q. Zheng, B. Hui, T. Y. Zhuo, S. Singh, X. Tang, L. von Werra, and S. Longpre. Octopack: Instruction tuning code large language models, 2023. find
  44. nickrosh. Open Source Implementation of Evol-Instruct-Code. https://huggingface.co/ datasets/nickrosh/Evol-Instruct-Code-80k-v1, 2023. ↗
  45. E. Nijkamp, B. Pang, H. Hayashi, L. Tu, H. Wang, Y. Zhou, S. Savarese, and C. Xiong. Codegen: An open large language model for code with multi-turn program synthesis. In The Eleventh International Conference on Learning Representations, 2023. find
  46. OpenAI. Chatgpt: Optimizing language models for dialogue. https://openai.com/blog/ chatgpt/, 2022. ↗
  47. OpenAI. Gpt-4 technical report, 2023.
  48. OpenAI. Terms of service, 3 2023. Accessed: August 17, 2023. find
  49. OpenAI. Gpt-4o system card. 2024.
  50. L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. L. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray, J. Schulman, J. Hilton, F. Kelton, L. Miller, M. Simens, A. Askell, P. Welinder, P. Christiano, J. Leike, and R. Lowe. Training language models to follow instructions with human feedback, 20…
  51. R. Pan, A. R. Ibrahimzada, R. Krishna, D. Sankar, L. P. Wassi, M. Merler, B. Sobolev, R. Pavuluri, S. Sinha, and R. Jabbarvand. Understanding the effectiveness of large language models in code translation. arXiv preprint arXiv:2308.03109, 2023. find
  52. A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever. Improving language understanding by generative pre-training. 2018. find
  53. R. Rafailov, A. Sharma, E. Mitchell, C. D. Manning, S. Ermon, and C. Finn. Direct preference optimization: Your language model is secretly a reward model. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  54. S. Rajbhandari, J. Rasley, O. Ruwase, and Y. He. Zero: memory optimizations toward training trillion parameter models. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC ’20. IEEE Press, 2020. find
  55. S. A. Research. Snowflake arctic: The best llm for enterprise ai — efficiently intelligent, truly open, April 24 2024. Accessed: 2024-05-22. find
  56. B. Roziere, M.-A. Lachaux, L. Chanussot, and G. Lample. Unsupervised translation of programming languages. Advances in neural information processing systems, 33:20601–20611, 2020.
  57. B. Rozière, J. Gehring, F. Gloeckle, S. Sootla, I. Gat, X. E. Tan, Y. Adi, J. Liu, T. Remez, J. Rapin, A. Kozhevnikov, I. Evtimov, J. Bitton, M. Bhatt, C. C. Ferrer, A. Grattafiori, W. Xiong, A. Défossez, J. Copet, F. Azhar, H. Touvron, L. Martin, N. Usunier, T. Scialom, and G. Synnaeve. Code llama:… — Code Llama: Open Foundation Models for Code
  58. N. Shazeer and M. Stern. Adafactor: Adaptive learning rates with sublinear memory cost, 2018. find
  59. A. Shypula, A. Madaan, Y. Zeng, U. Alon, J. Gardner, M. Hashemi, G. Neubig, P. Ranganathan, O. Bastani, and A. Yazdanbakhsh. Learning performance-improving code edits. arXiv preprint arXiv:2302.07867, 2023. find
  60. Z. Sun, Y. Shen, H. Zhang, Q. Zhou, Z. Chen, D. D. Cox, Y. Yang, and C. Gan. SALMON: Self-alignment with instructable reward models. In The Twelfth International Conference on Learning Representations, 2024.
  61. Z. Sun, Y. Shen, Q. Zhou, H. Zhang, Z. Chen, D. D. Cox, Y. Yang, and C. Gan. Principle-driven self-alignment of language models from scratch with minimal human supervision. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  62. C. Team, H. Zhao, J. Hui, J. Howland, N. Nguyen, S. Zuo, A. Hu, C. A. Choquette-Choo, J. Shen, J. Kelley, K. Bansal, L. Vilnis, M. Wirth, P. Michel, P. Choy, P. Joshi, R. Kumar, S. Hashmi, S. Agrawal, Z. Gong, J. Fine, T. Warkentin, A. J. Hartman, B. Ni, K. Korevec, K. Schaefer, and S. Huffman. Code… — CodeGemma: Open Code Models Based on Gemma
  63. G. Team. Gemini: A family of highly capable multimodal models, 2024.
  64. Q. Team. Code with codeqwen1.5, April 16 2024. Accessed: 2024-05-20. find
  65. theblackcat102. The evolved code alpaca dataset. https://huggingface.co/datasets/ theblackcat102/evol-codealpaca-v1, 2023. ↗
  66. H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y. Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale, D. Bikel, L. Blecher, C. C. Ferrer, M. Chen, G. Cucurull, D. Esiobu, J. Fernandes, J. Fu, W. Fu, B. Fuller, C. Gao, V. Goswami, N. Goyal, A. Hartshorn, S. Hosseini, R. Hou, H. Inan,… — Llama 2: Open Foundation and Fine-Tuned Chat Models
  67. X. Wang, B. Li, Y. Song, F. F. Xu, X. Tang, M. Zhuge, J. Pan, Y. Song, B. Li, J. Singh, H. H. Tran, F. Li, R. Ma, M. Zheng, B. Qian, Y. Shao, N. Muennighoff, Y. Zhang, B. Hui, J. Lin, R. Brennan, H. Peng, H. Ji, and G. Neubig. Openhands: An open platform for ai software developers as generalist agen… — OpenHands: An Open Platform for AI Software Developers as Generalist Agents
  68. Y. Wang, Y. Kordi, S. Mishra, A. Liu, N. A. Smith, D. Khashabi, and H. Hajishirzi. Self-instruct: Aligning language models with self-generated instructions. In A. Rogers, J. Boyd-Graber, and N. Okazaki, editors, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics… find
  69. Y. Wang, H. Le, A. D. Gotmare, N. D. Q. Bui, J. Li, and S. C. H. Hoi. Codet5+: Open code large language models for code understanding and generation, 2023. find
  70. Y. Wang, W. Wang, S. Joty, and S. C. Hoi. CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. In M.-F. Moens, X. Huang, L. Specia, and S. W.-t. Yih, editors, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing,… find
  71. Y. Wei, H. Han, and R. Samdani. Arctic-snowcoder: Demystifying high-quality data in code pretraining. arXiv preprint arXiv:2409.02326, 2024. — [arXiv:2409.02326](https://arxiv.org/abs/2409.02326) find
  72. Y. Wei, Z. Wang, J. Liu, Y. Ding, and L. Zhang. Magicoder: Source code is all you need. arXiv preprint arXiv:2312.02120, 2023. find
  73. Y. Wei, C. S. Xia, and L. Zhang. Copiloting the copilots: Fusing large language models with completion engines for automated program repair. In Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2023, page 172… find
  74. M. Weyssow, A. Kamanda, and H. Sahraoui. Codeultrafeedback: An llm-as-a-judge dataset for aligning large language models to coding preferences. arXiv preprint arXiv:2403.09032, 2024. — [arXiv:2403.09032](https://arxiv.org/abs/2403.09032) find
  75. C. S. Xia, Y. Deng, S. Dunn, and L. Zhang. Agentless: Demystifying llm-based software engineering agents. arXiv preprint, 2024. find
  76. C. S. Xia, Y. Deng, and L. Zhang. Top leaderboard ranking= top coding proficiency, always? evoeval: Evolving coding benchmarks via llm. arXiv preprint arXiv:2403.19114, 2024. — [arXiv:2403.19114](https://arxiv.org/abs/2403.19114) find
  77. C. S. Xia, M. Paltenghi, J. L. Tian, M. Pradel, and L. Zhang. Universal fuzzing via large language models, 2023. find
  78. C. S. Xia, Y. Wei, and L. Zhang. Automated program repair in the era of large pre-trained language models. In 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), pages 1482–1494, 2023. find
  79. C. S. Xia and L. Zhang. Less training, more repairing please: Revisiting automated program repair via zero-shot learning, 2022. find
  80. J. Yang, C. E. Jimenez, A. Wettig, K. Lieret, S. Yao, K. Narasimhan, and O. Press. Swe-agent: Agent-computer interfaces enable automated software engineering, 2024.
  81. Z. Yu, X. Zhang, N. Shang, Y. Huang, C. Xu, Y. Zhao, W. Hu, and Q. Yin. Wavecoder: Widespread and versatile enhanced instruction tuning with refined data generation, 2024. find
  82. W. Yuan, R. Y. Pang, K. Cho, X. Li, S. Sukhbaatar, J. Xu, and J. Weston. Self-rewarding language models, 2024. find
  83. T. Zheng, G. Zhang, T. Shen, X. Liu, B. Y. Lin, J. Fu, W. Chen, and X. Yue. Opencodeinterpreter: Integrating code generation with execution and refinement. arXiv preprint arXiv:2402.14658, 2024. find
  84. T. Y. Zhuo, M. C. Vu, J. Chim, H. Hu, W. Yu, R. Widyasari, I. N. B. Yusuf, H. Zhan, J. He, I. Paul, S. Brunner, C. Gong, T. Hoang, A. R. Zebaze, X. Hong, W.-D. Li, J. Kaddour, M. Xu, Z. Zhang, P. Yadav, N. Jain, A. Gu, Z. Cheng, J. Liu, Q. Liu, Z. Wang, D. Lo, B. Hui, N. Muennighoff, D. Fried, X. Du… — BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wei-2024-selfcodealign-self-alignment-code-generation/