This work introduces (1) a technique that allows large language models (LLMs) to leverage user-provided code when solving programming tasks and (2) a method to iteratively generate modular sub-functions that can aid future code generation attempts when the initial code generated by the LLM is inadequate. Generating computer programs in general-purpose programming languages like Python poses a challenge for LLMs when instructed to use code provided in the prompt. Code-specific LLMs (e.g., GitHub Copilot, CodeLlama2) can generate code completions in real-time by drawing on all code available in a development environment. However, restricting code-specific LLMs to use only in-context code is not straightforward, as the model is not explicitly instructed to use the user-provided code and users cannot highlight precisely which snippets of code the model should incorporate into its context. Moreover, current systems lack effective recovery methods, forcing users to iteratively re-prompt the model with modified prompts until a sufficient solution is reached. Our method differs from traditional LLM-powered code-generation by constraining code-generation to an explicit function set and enabling recovery from failed attempts through automatically generated sub-functions. When the LLM cannot produce working code, we generate modular sub-functions to aid subsequent attempts at generating functional code. A by-product of our method is a library of reusable sub-functions that can solve related tasks, imitating a software team where efficiency scales with experience. We also introduce a new "half-shot" evaluation paradigm that provides tighter estimates of LLMs' coding abilities compared to traditional zero-shot evaluation. Our proposed evaluation method encourages models to output solutions in a structured format, decreasing syntax errors that can be mistaken for poor coding ability.
翻译:暂无翻译