CODEPROMPTZIP: Compressing Code Prompt for Retrieval-Augmented Generation in Coding Tasks with LMs

ACL ARR 2025 February Submission1524 Authors

Abstract: Retrieval-Augmented Generation (RAG) enhances coding tasks by incorporating retrieved code examples into prompts. However, lengthy prompts—often exceeding tens of thousands of tokens—introduce challenges related to limited context windows of language models (LMs) and high computational costs. Existing prompt compression techniques focus on natural language, lacking tailored solutions for code. To address the gap, we propose CODEPROMPTZIP, a framework that compresses code examples before integrating into RAG workflows. Our framework employs a type-aware, priority-driven strategy to construct training samples for code compression. Using program analysis, we identify token types (e.g., Identifier) and perform ablation analysis to rank their removal priorities based on their impact on task performance. We then train a small LM as the compressor on these samples, enabling flexible compression conditioned on specified ratios while minimizing performance degradation. Specially, the compressor’s architecture is augmented with a copy mechanism, allowing tokens to be directly copied from the original code snippets. Evaluation results show that CODEPROMPTZIP surpasses SOTA entropy-based and distillation-based baselines, improving by 23.4%, 28.7%, and 8.7% over the best baseline for Assertion Generation, Bugs2Fix, and Code Suggestion, respectively.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: retrieval-augmented generation, code generation and understanding, prompting

Contribution Types: Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models

Languages Studied: Programming Language, Java, English

Submission Number: 1524