# BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning

arXiv: https://arxiv.org/abs/2407.17631 · HTML: https://mlsanity.com/paper/2407.17631/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 92 references that are in the map.
- First posted on arXiv 24 Jul 2024.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [Sparse, Dense, and Attentional Representations for Text Retrieval](https://mlsanity.com/paper/2005.00181/) (2020)
- [Parallel Context Windows for Large Language Models](https://mlsanity.com/paper/2212.10947/) (2022)
- [Efficient Long-Text Understanding with Short-Text Models](https://mlsanity.com/paper/2208.00748/) (2022)
- [Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation](https://mlsanity.com/paper/2102.01818/) (2021)
- [Large Language Models for Test-Free Fault Localization](https://mlsanity.com/paper/2310.01726/) (2023)
- [Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models](https://mlsanity.com/paper/2201.10582/) (2022)
- [Text-based Question Answering from Information Retrieval and Deep Neural Network Perspectives: A Survey](https://mlsanity.com/paper/2002.06612/) (2020)
- [Fast Changeset-based Bug Localization with BERT](https://mlsanity.com/paper/2112.14169/) (2021)
- [Pre-training Code Representation with Semantic Flow Graph for Effective Bug Localization](https://mlsanity.com/paper/2308.12773/) (2023)
- [RLocator: Reinforcement Learning for Bug Localization](https://mlsanity.com/paper/2305.05586/) (2023)
- [RRF102: Meeting the TREC-COVID Challenge with a 100+ Runs Ensemble](https://mlsanity.com/paper/2010.00200/) (2020)
- [CodeMatcher: Searching Code Based on Sequential Semantics of Important Query Words](https://mlsanity.com/paper/2005.14373/) (2020)
- [Industry-scale IR-based Bug Localization: A Perspective from Facebook](https://mlsanity.com/paper/2010.09977/) (2020)
- [Mutation-based Fault Localization of Deep Neural Networks](https://mlsanity.com/paper/2309.05067/) (2023)
- [Balancing Reinforcement Learning Training Experiences in Interactive Information Retrieval](https://mlsanity.com/paper/2006.03185/) (2020)
- [BoostNSift: A Query Boosting and Code Sifting Technique for Method Level Bug Localization](https://mlsanity.com/paper/2108.12901/) (2021)

## Built on by (most cited first, 7 of 7)

- [Does SWE-Bench-Verified Test Agent Ability or Model Memory?](https://mlsanity.com/paper/2512.10218/) (2025)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language Models](https://mlsanity.com/paper/2601.18044/) (2026)
- [Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic Cognition](https://mlsanity.com/paper/2601.12522/) (2026)
- [XAgent: eXecution-guided Agentic AI for Effective Localization and Resolution of GitHub Issues](https://mlsanity.com/paper/2609.09769/) (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)

Software bugs require developers to exert significant effort to identify and resolve them, often consuming about one-third of their time. Bug localization, the process of pinpointing the exact source code files that need modification, is crucial in reducing this effort. Existing bug localization tools, typically reliant on deep learning techniques, face limitations in cross-project applicability and effectiveness in multi-language environments. Recent advancements with Large Language Models (LLMs) offer detailed representations for bug localization. However, they encounter challenges with limited context windows and mapping accuracy. To address these issues, we propose BLAZE, an approach that employs dynamic chunking and hard example learning. First, BLAZE dynamically segments source code to minimize continuity loss. Then, BLAZE fine-tunes a GPT-based model using challenging bug cases, in order to enhance cross-project and cross-language bug localization. To support the capability of BLAZE, we create the BEETLEBOX dataset, which comprises 26,321 bugs from 29 large and thriving open-source projects across five different programming languages (Java, C++, Python, Go, and JavaScript). Our evaluations of BLAZE on three benchmark datasets BEETLEBOX, SWE-Bench, and Ye et al. demonstrate substantial improvements compared to six state-of-the-art baselines. Specifically, BLAZE achieves up to an increase of 120% in Top 1 accuracy, 144% in Mean Average Precision (MAP), and 100% in Mean Reciprocal Rank (MRR). An extensive ablation study confirms the contributions of our pipeline components to the overall performance enhancement.