CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement

Guardado en:
Detalles Bibliográficos
Publicado en:arXiv.org (Dec 19, 2024), p. n/a
Autor principal: Leitian Tao
Otros Autores: Chen, Xiang, Yu, Tong, Tung Mai, Rossi, Ryan, Li, Yixuan, Mitra, Saayan
Publicado:
Cornell University Library, arXiv.org
Materias:
Acceso en línea:Citation/Abstract
Full text outside of ProQuest
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Resumen:Large Language Models (LLMs) have revolutionized code generation but require significant resources and often over-generalize, limiting their task-specific efficiency. Fine-tuning smaller, open-source LLMs provides a cost-effective alternative. However, standard supervised approaches rely only on correct examples, missing valuable insights from failures. We introduce CodeLutra, a framework that leverages both correct and incorrect code attempts. Instead of using only correct solutions, CodeLutra applies iterative preference-based refinement, comparing successful and failed outputs to better approximate desired results. This approach narrows the performance gap with state-of-the-art larger models without requiring massive datasets or auxiliary models. For instance, on a challenging data science coding task, using only 500 samples improved Llama-3-8B's accuracy from 28.2% to 48.6%, approaching GPT-4's level. By learning from both successes and mistakes, CodeLutra provides a scalable and efficient path to high-quality code generation, making smaller open-source models more competitive with leading closed-source alternatives.
ISSN:2331-8422
Fuente:Engineering Database