CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval
By: Jiahui Geng , Fengyu Cai , Shaobo Cui and more
Potential Business Impact:
Helps find better, safer computer code.
Code retrieval is essential in modern software development, as it boosts code reuse and accelerates debugging. However, current benchmarks primarily emphasize functional relevance while neglecting critical dimensions of software quality. Motivated by this gap, we introduce CoQuIR, the first large-scale, multilingual benchmark specifically designed to evaluate quality-aware code retrieval across four key dimensions: correctness, efficiency, security, and maintainability. CoQuIR provides fine-grained quality annotations for 42,725 queries and 134,907 code snippets in 11 programming languages, and is accompanied by two quality-centric evaluation metrics: Pairwise Preference Accuracy and Margin-based Ranking Score. Using CoQuIR, we benchmark 23 retrieval models, covering both open-source and proprietary systems, and find that even top-performing models frequently fail to distinguish buggy or insecure code from their more robust counterparts. Furthermore, we conduct preliminary investigations into training methods that explicitly encourage retrievers to recognize code quality. Using synthetic datasets, we demonstrate promising improvements in quality-aware metrics across various models, without sacrificing semantic relevance. Downstream code generation experiments further validate the effectiveness of our approach. Overall, our work highlights the importance of integrating quality signals into code retrieval systems, laying the groundwork for more trustworthy and robust software development tools.
Similar Papers
UniCoR: Modality Collaboration for Robust Cross-Language Hybrid Code Retrieval
Software Engineering
Finds code faster using words and examples.
Improving IR-based Bug Localization with Semantics-Driven Query Reduction
Software Engineering
Finds software bugs faster by understanding code.
VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding
CV and Pattern Recognition
Helps computers find answers in any language document.