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

Gardado en:
Detalles Bibliográficos
Publicado en:arXiv.org (Aug 19, 2024), p. n/a
Autor Principal: Chakraborty, Partha
Outros autores: Alfadel, Mahmoud, Nagappan, Meiyappan
Publicado:
Cornell University Library, arXiv.org
Materias:
Acceso en liña:Citation/Abstract
Full text outside of ProQuest
Etiquetas: Engadir etiqueta
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!

MARC

LEADER 00000nab a2200000uu 4500
001 3084969526
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3084969526 
045 0 |b d20240819 
100 1 |a Chakraborty, Partha 
245 1 |a BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning 
260 |b Cornell University Library, arXiv.org  |c Aug 19, 2024 
513 |a Working Paper 
520 3 |a 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. 
653 |a Accuracy 
653 |a Datasets 
653 |a Python 
653 |a Source code 
653 |a Large language models 
653 |a Deep learning 
653 |a Localization 
653 |a Programming languages 
653 |a Windows (computer programs) 
653 |a Ablation 
700 1 |a Alfadel, Mahmoud 
700 1 |a Nagappan, Meiyappan 
773 0 |t arXiv.org  |g (Aug 19, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3084969526/abstract/embedded/H09TXR3UUZB2ISDL?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2407.17631