Evaluating the Generalizability of LLMs in Automated Program Repair

• URL: http://arxiv.org/abs/2503.09217v1
• Date: Wed, 12 Mar 2025 10:03:58 GMT
• Title: Evaluating the Generalizability of LLMs in Automated Program Repair
• Authors: Fengjie Li, Jiajun Jiang, Jiajun Sun, Hongyu Zhang,
• Abstract summary: We evaluate 11 top-performing LLMs on DEFECTS4J-TRANS, a new dataset derived from transforming Defects4J.<n>Results from experiments on both Defects4J and DEFECTS4J-TRANS show that all studied LLMs have limited generalizability in APR tasks.
• Score: 12.7034916462208
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: LLM-based automated program repair methods have attracted significant attention for their state-of-the-art performance. However, they were primarily evaluated on a few well known datasets like Defects4J, raising questions about their effectiveness on new datasets. In this study, we evaluate 11 top-performing LLMs on DEFECTS4J-TRANS, a new dataset derived from transforming Defects4J while maintaining the original semantics. Results from experiments on both Defects4J and DEFECTS4J-TRANS show that all studied LLMs have limited generalizability in APR tasks, with the average number of correct and plausible patches decreasing by 49.48% and 42.90%, respectively, on DEFECTS4J-TRANS. Further investigation into incorporating additional repair-relevant information in repair prompts reveals that, although this information significantly enhances the LLMs' capabilities (increasing the number of correct and plausible patches by up to 136.67% and 121.82%, respectively), performance still falls short of their original results. This indicates that prompt engineering alone is insufficient to substantially enhance LLMs' repair capabilities. Based on our study, we also offer several recommendations for future research.

Related papers

• Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis [78.07225438556203]
  We introduce LLM-Oasis, the largest resource for training end-to-end factuality evaluators. It is constructed by extracting claims from Wikipedia, falsifying a subset of these claims, and generating pairs of factual and unfactual texts. We then rely on human annotators to both validate the quality of our dataset and to create a gold standard test set for factuality evaluation systems.
  arXiv  Detail & Related papers  (2024-11-29T12:21:15Z)
• Beyond ChatGPT: Enhancing Software Quality Assurance Tasks with Diverse LLMs and Validation Techniques [14.230480872339463]
  This paper investigates the capabilities of several Large Language Models (LLMs) across two SQA tasks: fault localization and vulnerability detection. By implementing a voting mechanism to combine the LLMs' results, we achieved more than a 10% improvement over the GPT-3.5 in both tasks. This approach led to performance improvements of 16% in fault localization and 12% in vulnerability detection compared to the GPT-3.5, with a 4% improvement compared to the best-performed LLMs.
  arXiv  Detail & Related papers  (2024-09-02T07:26:19Z)
• See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses [51.975495361024606]
  We propose a Self-Challenge evaluation framework with human-in-the-loop. Starting from seed instances that GPT-4 fails to answer, we prompt GPT-4 to summarize error patterns that can be used to generate new instances. We then build a benchmark, SC-G4, consisting of 1,835 instances generated by GPT-4 using these patterns, with human-annotated gold responses.
  arXiv  Detail & Related papers  (2024-08-16T19:01:52Z)
• Exploring Automatic Cryptographic API Misuse Detection in the Era of LLMs [60.32717556756674]
  This paper introduces a systematic evaluation framework to assess Large Language Models in detecting cryptographic misuses. Our in-depth analysis of 11,940 LLM-generated reports highlights that the inherent instabilities in LLMs can lead to over half of the reports being false positives. The optimized approach achieves a remarkable detection rate of nearly 90%, surpassing traditional methods and uncovering previously unknown misuses in established benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T15:31:26Z)
• CREF: An LLM-based Conversational Software Repair Framework for Programming Tutors [8.415004837059863]
  It is crucial to recognize that existing repair benchmarks may have influenced LLM training data, potentially causing data leakage. Our work assesses the repair performance of 12 LLMs on TutorCode, measuring repair correctness (TOP-5 and AVG-5) and patch precision (RPSR) To fully harness LLMs' conversational capabilities and the benefits of augmented information, we introduce a novel conversational semi-automatic repair framework CREF assisting human tutor.
  arXiv  Detail & Related papers  (2024-06-20T03:36:34Z)
• Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis [12.7034916462208]
  Automated Program Repair (APR) has garnered significant attention due to its potential to streamline the bug repair process for human developers. This paper introduces an innovative APR approach called GIANTREPAIR. Based on this insight, GIANTREPAIR first constructs patch skeletons from LLM-generated patches to confine the patch space, and then generates high-quality patches tailored to specific programs.
  arXiv  Detail & Related papers  (2024-06-03T05:05:12Z)
• How Far Can We Go with Practical Function-Level Program Repair? [11.71750828464698]
  This paper investigates the effect of few-shot learning mechanism and the auxiliary repair-relevant information on function-level APR. We propose an LLM-based function-level APR technique, namely SRepair, which adopts a dual-LLM framework to leverage the power of the auxiliary repair-relevant information.
  arXiv  Detail & Related papers  (2024-04-19T12:14:09Z)
• Aligning the Objective of LLM-based Program Repair [14.935596175148586]
  This paper investigates a new approach to adapt large language models (LLMs) to program repair.<n>Our core insight is that LLM's APR capability can be greatly improved by simply aligning the output to their training objective.<n>Based on this insight, we designed D4C, a straightforward prompting framework for APR.
  arXiv  Detail & Related papers  (2024-04-13T02:36:40Z)
• LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement [79.31084387589968]
  Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. We propose LLM2LLM, a data augmentation strategy that uses a teacher LLM to enhance a small seed dataset. We achieve improvements up to 24.2% on the GSM8K dataset, 32.6% on CaseHOLD, 32.0% on SNIPS, 52.6% on TREC and 39.8% on SST-2 over regular fine-tuning in the low-data regime.
  arXiv  Detail & Related papers  (2024-03-22T08:57:07Z)
• Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning [79.32236399694077]
  Low-quality data in the training set are usually detrimental to instruction tuning. We propose a novel method, termed "reflection-tuning" This approach utilizes an oracle LLM to recycle the original training data by introspecting and enhancing the quality of instructions and responses in the data.
  arXiv  Detail & Related papers  (2023-10-18T05:13:47Z)
• TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
  Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
  arXiv  Detail & Related papers  (2023-10-10T16:38:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.