Zero-Shot Cross-Domain Code Search without Fine-Tuning

2025-04-10

AI Summary

To address the high fine-tuning cost and poor cross-domain generalization in zero-shot cross-domain code search, this paper proposes a fine-tuning-free dual-path semantic alignment paradigm. It decouples query–code matching into two complementary paths: query–pseudo-comment matching and code–pseudo-code matching. Leveraging large language models (LLMs), it generates high-quality pseudo-annotations; then integrates pre-trained language model (PLM)-based similarity scoring with strategic sampling to achieve robust cross-domain semantic alignment. Evaluated on three benchmark datasets, our method achieves average MRR improvements of 21.4% and 24.9% over CoCoSoDa and UniXcoder, respectively—matching or even surpassing the performance of the fine-tuned RAPID baseline. To the best of our knowledge, this is the first approach to enable efficient, robust zero-shot cross-domain code retrieval without any task-specific adaptation.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Code search aims to retrieve semantically relevant code snippets for natural language queries. While pre-trained language models (PLMs) have shown remarkable performance in this task, they struggle in cross-domain scenarios, often requiring costly fine-tuning or facing performance drops in zero-shot settings. RAPID, which generates synthetic data for model fine-tuning, is currently the only effective method for zero-shot cross-domain code search. Despite its effectiveness, RAPID demands substantial computational resources for fine-tuning and needs to maintain specialized models for each domain, underscoring the need for a zero-shot, fine-tuning-free approach for cross-domain code search. The key to tackling zero-shot cross-domain code search lies in bridging the gaps among domains. In this work, we propose to break the query-code matching process of code search into two simpler tasks: query-comment matching and code-code matching. Our empirical study reveals the strong complementarity among the three matching schemas in zero-shot cross-domain settings, i.e., query-code, query-comment, and code-code matching. Based on the findings, we propose CodeBridge, a zero-shot, fine-tuning-free approach for cross-domain code search. Specifically, CodeBridge uses Large Language Models (LLMs) to generate comments and pseudo-code, then combines query-code, query-comment, and code-code matching via PLM-based similarity scoring and sampling-based fusion. Experimental results show that our approach outperforms the state-of-the-art PLM-based code search approaches, i.e., CoCoSoDa and UniXcoder, by an average of 21.4% and 24.9% in MRR, respectively, across three datasets. Our approach also yields results that are better than or comparable to those of the zero-shot cross-domain code search approach RAPID, which requires costly fine-tuning.

Problem

• Enables zero-shot cross-domain code search without fine-tuning
• Bridges domain gaps via query-comment and code-code matching
• Outperforms existing methods in accuracy and resource efficiency

Innovation

• LLM-generated comments and pseudo-code
• PLM-based similarity scoring fusion
• Zero-shot fine-tuning-free code search