@inproceedings{gupta-etal-2025-sacl,
    title = "{SACL}: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization",
    author = "Gupta, Dhruv  and
      Lakshmy, Gayathri Ganesh  and
      Xie, Yiqing",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.1365/",
    doi = "10.18653/v1/2025.findings-emnlp.1365",
    pages = "25052--25065",
    ISBN = "979-8-89176-335-7",
    abstract = "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)."
}