REVIEW 10 cited by
Large Language Models in Fault Localisation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Large Language Models in Fault Localisation
read the original abstract
Large Language Models (LLMs) have shown promise in multiple software engineering tasks including code generation, program repair, code summarisation, and test generation. Fault localisation is instrumental in enabling automated debugging and repair of programs and was prominently featured as a highlight during the launch event of ChatGPT-4. Nevertheless, the performance of LLMs compared to state-of-the-art methods, as well as the impact of prompt design and context length on their efficacy, remains unclear. To fill this gap, this paper presents an in-depth investigation into the capability of ChatGPT-3.5 and ChatGPT-4, the two state-of-the-art LLMs, on fault localisation. Using the widely-adopted large-scale Defects4J dataset, we compare the two LLMs with the existing fault localisation techniques. We also investigate the consistency of LLMs in fault localisation, as well as how prompt engineering and the length of code context affect the fault localisation effectiveness. Our findings demonstrate that within function-level context, ChatGPT-4 outperforms all the existing fault localisation methods. Additional error logs can further improve ChatGPT models' localisation accuracy and consistency, with an average 46.9% higher accuracy over the state-of-the-art baseline SmartFL on the Defects4J dataset in terms of TOP-1 metric. However, when the code context of the Defects4J dataset expands to the class-level, ChatGPT-4's performance suffers a significant drop, with 49.9% lower accuracy than SmartFL under TOP-1 metric. These observations indicate that although ChatGPT can effectively localise faults under specific conditions, limitations are evident. Further research is needed to fully harness the potential of LLMs like ChatGPT for practical fault localisation applications.
Forward citations
Cited by 10 Pith papers
-
Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning
LLMVD.js uses LLM agents to confirm 84% of taint-style vulnerabilities on public benchmarks (vs. <22% for prior tools) and generates validated exploits for 36 of 260 new packages (vs. ≤2 for traditional tools).
-
PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents
A multi-agent repair framework that samples multiple edit locations and iteratively reflects on patch attempts reaches 76.0% Pass@1 on SWE-bench-Verified, up to a 7.8% relative gain over SWE-agent.
-
Towards Better Linux Kernel Fault Localization: Leveraging Contrastive Reasoning and Hierarchical Context Analysis
CoHiKer improves Top-1 fault localization accuracy in the Linux kernel by up to 26% at file level and 57% at method level over prior LLM baselines via contrastive reasoning and hierarchical context analysis.
-
BLAgent: Agentic RAG for File-Level Bug Localization
BLAgent achieves over 78% Top-1 accuracy on SWE-bench Lite for file-level bug localization using agentic RAG, at 18x lower cost than baselines, and boosts end-to-end APR success by over 20%.
-
BLAgent: Agentic RAG for File-Level Bug Localization
BLAgent achieves over 78% top-1 file-level bug localization accuracy on SWE-bench-Lite with open-source models and over 86% with closed-source models while being over 18x cheaper than the strongest baseline.
-
Towards Explorative IRBL: Combining Semantic Retrieval with LLM-driven Iterative Code Exploration
GenLoc integrates semantic retrieval and LLM-based iterative code exploration to outperform prior IRBL and LLM methods on Java and Python bug localization benchmarks.
-
SysLLMatic: Large Language Models are Software System Optimizers
SysLLMatic integrates LLMs with performance diagnostics and a 43-pattern catalog to optimize complex software, reporting 1.54x latency and 1.24x energy gains over compilers on large Java systems where prior LLM method...
-
Agentless: Demystifying LLM-based Software Engineering Agents
Agentless, a basic three-phase LLM pipeline for bug localization, repair, and validation, outperforms complex open-source agents on SWE-bench Lite with 32% success rate at $0.70 cost.
-
LLM-Based Automated Diagnosis Of Integration Test Failures At Google
Auto-Diagnose applies LLMs to summarize and diagnose root causes of integration test failures, reporting 90.14% accuracy on 71 manual cases and positive adoption after Google-wide rollout.
-
Large Language Models for Fault Localization: An Empirical Study
An empirical study of four LLMs for statement-level Java fault localization finds Gemini-2.5-Flash most accurate, bug-report context strongly helpful, and few-shot/CoT gains inconsistent.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.