# Fast Changeset-based Bug Localization with BERT

arXiv: https://arxiv.org/abs/2112.14169 · HTML: https://mlsanity.com/paper/2112.14169/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2021.

## Built on by (most cited first, 13 of 13)

- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Is ChatGPT the Ultimate Programming Assistant -- How far is it?](https://mlsanity.com/paper/2304.11938/) (2023)
- [RLocator: Reinforcement Learning for Bug Localization](https://mlsanity.com/paper/2305.05586/) (2023)
- [BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning](https://mlsanity.com/paper/2407.17631/) (2024)
- [Improved IR-based Bug Localization with Intelligent Relevance Feedback](https://mlsanity.com/paper/2501.10542/) (2025)
- [Generative AI for Self-Adaptive Systems: State of the Art and Research Roadmap](https://mlsanity.com/paper/2512.04680/) (2025)
- [Generative transformations and patterns in LLM-native approaches for software verification and falsification](https://mlsanity.com/paper/2404.09384/) (2024)
- [Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults](https://mlsanity.com/paper/2505.19489/) (2025)
- [Exploring Large Language Models in Resolving Environment-Related Crash Bugs: Localizing and Repairing](https://mlsanity.com/paper/2312.10448/) (2023)
- [Studying the Impact of TensorFlow and PyTorch Bindings on Machine Learning Software Quality](https://mlsanity.com/paper/2407.05466/) (2024)
- [Skill over Scale: The Case for Medium, Domain-Specific Models for SE](https://mlsanity.com/paper/2306.03268/) (2023)
- [Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic Cognition](https://mlsanity.com/paper/2601.12522/) (2026)
- [From Codebase to Culprit (C2C): Reducing the Search Space for Bugs with Semantic Retrieval and Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2609.38402/) (2026)

## Abstract (arXiv)

Automatically localizing software bugs to the changesets that induced them has the potential to improve software developer efficiency and to positively affect software quality. To facilitate this automation, a bug report has to be effectively matched with source code changes, even when a significant lexical gap exists between natural language used to describe the bug and identifier naming practices used by developers. To bridge this gap, we need techniques that are able to capture software engineering-specific and project-specific semantics in order to detect relatedness between the two types of documents that goes beyond exact term matching. Popular transformer-based deep learning architectures, such as BERT, excel at leveraging contextual information, hence appear to be a suitable candidate for the task. However, BERT-like models are computationally expensive, which precludes them from being used in an environment where response time is important. In this paper, we describe how BERT can be made fast enough to be applicable to changeset-based bug localization. We also explore several design decisions in using BERT for this purpose, including how best to encode changesets and how to match bug reports to individual changes for improved accuracy. We compare the accuracy and performance of our model to a non-contextual baseline (i.e., vector space model) and BERT-based architectures previously used in software engineering. Our evaluation results demonstrate advantages in using the proposed BERT model compared to the baselines, especially for bug reports that lack any hints about related code elements.