Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant information. In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features while preserving code functionality. Our discoveries include: (1) although trained on code, current retrievers heavily rely on surface-level textual features (e.g., docstrings, identifier names), and (2) they exhibit a strong bias towards well-documented code, even if the documentation is irrelevant. Based on our discoveries, we propose SACL, a framework that enriches textual information and reduces bias by augmenting code or structural knowledge with semantic information. Extensive experiments show that SACL substantially improves code retrieval (e.g., by 12.8% / 9.4% / 7.0% Recall@1 on HumanEval / MBPP / SWE-Bench-Lite), which also leads to better code generation performance (e.g., by 4.88% Pass@1 on HumanEval).
@article{arxiv.2506.20081,
title = {SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization},
author = {Dhruv Gupta and Gayathri Ganesh Lakshmy and Yiqing Xie},
journal= {arXiv preprint arXiv:2506.20081},
year = {2025}
}