DDPT: Diffusion-Driven Prompt Tuning for Large Language Model Code Generation
This addresses the problem of manual prompt crafting for developers using LLMs in code generation, representing an incremental improvement in automation support.
The paper tackles the challenge of automating prompt engineering for large language model code generation by proposing Diffusion-Driven Prompt Tuning (DDPT), which learns to generate optimal prompt embeddings from Gaussian noise, resulting in improved prompt optimization as demonstrated in evaluation results.
Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation. However, the quality of the generated code is heavily dependent on the structure and composition of the prompts used. Crafting high-quality prompts is a challenging task that requires significant knowledge and skills of prompt engineering. To advance the automation support for the prompt engineering for LLM-based code generation, we propose a novel solution Diffusion-Driven Prompt Tuning (DDPT) that learns how to generate optimal prompt embedding from Gaussian Noise to automate the prompt engineering for code generation. We evaluate the feasibility of diffusion-based optimization and abstract the optimal prompt embedding as a directional vector toward the optimal embedding. We use the code generation loss given by the LLMs to help the diffusion model capture the distribution of optimal prompt embedding during training. The trained diffusion model can build a path from the noise distribution to the optimal distribution at the sampling phrase, the evaluation result demonstrates that DDPT helps improve the prompt optimization for code generation.