Impact of Large Language Models of Code on Fault Localization

Identifying the point of error is imperative in software debugging. Traditional fault localization (FL) techniques rely on executing the program and using the code coverage matrix in tandem with test case results to calculate a suspiciousness score for each method or line. Recently, learning-based F...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2025 IEEE Conference on Software Testing, Verification and Validation (ICST) s. 302 - 313
Hlavní autoři: Ji, Suhwan, Lee, Sanghwa, Lee, Changsup, Han, Yo-Sub, Im, Hyeonseung
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 31.03.2025
Témata:
Benchmark testing
Codes
Computer architecture
Deep Learning
Fault Localization
Feature extraction
Fine-Tuning
Large Language Model of Code
Large language models
Location awareness
Software debugging
Software engineering
Software testing
Source coding
Vulnerability Detection
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Identifying the point of error is imperative in software debugging. Traditional fault localization (FL) techniques rely on executing the program and using the code coverage matrix in tandem with test case results to calculate a suspiciousness score for each method or line. Recently, learning-based FL techniques have harnessed machine learning models to extract meaningful features from the code coverage matrix and improve FL performance. These techniques, however, require compilable source code, existing test cases, and specialized tools for generating the code coverage matrix for each programming language of interest. In this paper, we propose, for the first time, a simple but effective sequence generation approach for fine-tuning large language models of code (LLMCs) for FL tasks. LLMCs have recently received much attention for various software engineering problems. In line with these, we leverage the innate understanding of code that LLMCs have acquired through pre-training on large code corpora. Specifically, we fine-tune 13 representative encoder, encoder-decoder, and decoder-based LLMCs (across 7 different architectures) for FL tasks. Unlike previous approaches, LLM Cs can analyze code sequences that do not compile. Still, they have a limitation on the length of the input data. Therefore, for a fair comparison with existing FL techniques, we extract methods with errors from the project-level benchmark, Defects4J, and analyze them at the line level. Experimental results show that LLMCs fine-tuned with our approach successfully pinpoint error positions in 50.6%, 64.2%, and 72.3% of 1,291 methods in Defects4J for Top-1/3/5 prediction, outperforming the best learning-based state-of-the-art technique by up to 1.35, 1.12, and 1.08 times, respectively. We also conduct an in-depth investigation of key factors that may affect the FL performance of LLMCs. Our findings suggest promising research directions for FL and automated program repair tasks using LLMCs.
DOI:10.1109/ICST62969.2025.10989036