When Deep Learning Meets Information Retrieval-based Bug Localization: A Survey

TL;DR

The paper addresses the challenge of locating buggy code using bug reports by surveying deep learning–driven IR-based bug localization (IRBL) approaches. It synthesizes 61 primary studies to classify model architectures, data representations, and auxiliary features, and analyzes evaluation practices, datasets, and validation strategies. Key findings show that DL helps bridge lexical gaps and integrate code structure through semantic and syntactic representations, but challenges like cold-start, cross-project/language transfer, data quality, and interpretability persist. The work concludes with actionable directions, including broader language coverage, finer-grained localization, industry-oriented evaluation, and deeper exploration of large language models for IRBL.

Abstract

Bug localization is a crucial aspect of software maintenance, running through the entire software lifecycle. Information retrieval-based bug localization (IRBL) identifies buggy code based on bug reports, expediting the bug resolution process for developers. Recent years have witnessed significant achievements in IRBL, propelled by the widespread adoption of deep learning (DL). To provide a comprehensive overview of the current state of the art and delve into key issues, we conduct a survey encompassing 61 IRBL studies leveraging DL. We summarize best practices in each phase of the IRBL workflow, undertake a meta-analysis of prior studies, and suggest future research directions. This exploration aims to guide further advancements in the field, fostering a deeper understanding and refining practices for effective bug localization. Our study suggests that the integration of DL in IRBL enhances the model's capacity to extract semantic and syntactic information from both bug reports and source code, addressing issues such as lexical gaps, neglect of code structure information, and cold-start problems. Future research avenues for IRBL encompass exploring diversity in programming languages, adopting fine-grained granularity, and focusing on real-world applications. Most importantly, although some studies have started using large language models for IRBL, there is still a need for more in-depth exploration and thorough investigation in this area.

Figures (10)

• Figure 1: Primary Study Selection Process.
• Figure 2: Number of primary studies over the years.
• Figure 3: Distribution of venues.
• Figure 4: Framework of IRBL Approaches.
• Figure 5: Primary studies over the years.