Understanding the Effectiveness of LLMs in Automated Self-Admitted Technical Debt Repayment

• URL: http://arxiv.org/abs/2501.09888v1
• Date: Fri, 17 Jan 2025 00:23:44 GMT
• Title: Understanding the Effectiveness of LLMs in Automated Self-Admitted Technical Debt Repayment
• Authors: Mohammad Sadegh Sheikhaei, Yuan Tian, Shaowei Wang, Bowen Xu,
• Abstract summary: Self-Admitted Technical Debt (SATD) can degrade code quality and increase maintenance costs.<n>Large Language Models (LLMs) have shown promise in tasks like code generation and program repair.<n>We identify three key challenges in training and evaluating LLMs for SATD repayment.
• Score: 13.698224831089464
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Self-Admitted Technical Debt (SATD), cases where developers intentionally acknowledge suboptimal solutions in code through comments, poses a significant challenge to software maintainability. Left unresolved, SATD can degrade code quality and increase maintenance costs. While Large Language Models (LLMs) have shown promise in tasks like code generation and program repair, their potential in automated SATD repayment remains underexplored. In this paper, we identify three key challenges in training and evaluating LLMs for SATD repayment: (1) dataset representativeness and scalability, (2) removal of irrelevant SATD repayments, and (3) limitations of existing evaluation metrics. To address the first two dataset-related challenges, we adopt a language-independent SATD tracing tool and design a 10-step filtering pipeline to extract SATD repayments from repositories, resulting two large-scale datasets: 58,722 items for Python and 97,347 items for Java. To improve evaluation, we introduce two diff-based metrics, BLEU-diff and CrystalBLEU-diff, which measure code changes rather than whole code. Additionally, we propose another new metric, LEMOD, which is both interpretable and informative. Using our new benchmarks and evaluation metrics, we evaluate two types of automated SATD repayment methods: fine-tuning smaller models, and prompt engineering with five large-scale models. Our results reveal that fine-tuned small models achieve comparable Exact Match (EM) scores to prompt-based approaches but underperform on BLEU-based metrics and LEMOD. Notably, Gemma-2-9B leads in EM, addressing 10.1% of Python and 8.1% of Java SATDs, while Llama-3.1-70B-Instruct and GPT-4o-mini excel on BLEU-diff, CrystalBLEU-diff, and LEMOD metrics. Our work contributes a robust benchmark, improved evaluation metrics, and a comprehensive evaluation of LLMs, advancing research on automated SATD repayment.

Related papers

• Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models [8.70160958177614]
  Program synthesis with Large Language Models (LLMs) suffers from a "near-miss syndrome" We address this with a multi-agent framework called Synthesize, Execute, Instruct, Debug, and Repair (SEIDR) We empirically explore these trade-offs by comparing replace-focused, repair-focused, and hybrid debug strategies.
  arXiv  Detail & Related papers  (2025-03-10T16:56:51Z)
• SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models [4.875712300661656]
  We present SCORE ($mathbfS$ystematic $mathbfCO$nsistency and $mathbfR$obustness $mathbfE$valuation), a comprehensive framework for non-adversarial evaluation of Large Language Models. The SCORE framework evaluates models by repeatedly testing them on the same benchmarks in various setups to give a realistic estimate of their accuracy and consistency.
  arXiv  Detail & Related papers  (2025-02-28T19:27:29Z)
• SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution [56.9361004704428]
  Large Language Models (LLMs) have demonstrated remarkable proficiency across a variety of complex tasks.<n>We introduce SWE-Fixer, a novel open-source LLM designed to effectively and efficiently resolve GitHub issues.<n>We compile an extensive dataset that includes 110K GitHub issues along with their corresponding patches, and train the two modules of SWE-Fixer separately.
  arXiv  Detail & Related papers  (2025-01-09T07:54:24Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• Benchmarking Educational Program Repair [4.981275578987307]
  Large language models (LLMs) can be used to generate learning resources, improve error messages, and provide feedback on code. There is a pressing need for standardization and benchmarks that facilitate the equitable comparison of competing approaches. In this article, we propose a novel educational program repair benchmark.
  arXiv  Detail & Related papers  (2024-05-08T18:23:59Z)
• RepEval: Effective Text Evaluation with LLM Representation [55.26340302485898]
  RepEval is a metric that leverages the projection of Large Language Models (LLMs) representations for evaluation. Our work underscores the richness of information regarding text quality embedded within LLM representations, offering insights for the development of new metrics.
  arXiv  Detail & Related papers  (2024-04-30T13:50:55Z)
• Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
  We propose a new evaluation method, SQC-Score. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
  arXiv  Detail & Related papers  (2024-04-04T15:36:53Z)
• EntGPT: Linking Generative Large Language Models with Knowledge Bases [8.557683104631883]
  We introduce EntGPT, employing advanced prompt engineering to enhance EL tasks.<n>Our three-step hard-prompting method (EntGPT-P) significantly boosts the micro-F_1 score by up to 36% over vanilla prompts.<n>Our instruction tuning method (EntGPT-I) improves micro-F_1 scores by 2.1% on average in supervised EL tasks.
  arXiv  Detail & Related papers  (2024-02-09T19:16:27Z)
• Benchmarking Causal Study to Interpret Large Language Models for Source Code [6.301373791541809]
  This paper introduces a benchmarking strategy named Galeras comprised of curated testbeds for three SE tasks. We illustrate the insights of our benchmarking strategy by conducting a case study on the performance of ChatGPT under distinct prompt engineering methods.
  arXiv  Detail & Related papers  (2023-08-23T20:32:12Z)
• Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We? [17.128428286986573]
  This paper empirically investigates the extent to which technical debt can be automatically paid back by neural-based generative models. We start by extracting a dateset of 5,039 Self-Admitted Technical Debt (SATD) removals from 595 open-source projects. We use this dataset to experiment with seven different generative deep learning (DL) model configurations.
  arXiv  Detail & Related papers  (2023-08-17T12:27:32Z)
• Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy [68.31760483418901]
  Large Language Models(LLMs) struggle with providing current information due to the outdated pre-training data. Existing methods for updating LLMs, such as knowledge editing and continual fine-tuning, have significant drawbacks in generalizability of new information. We identify the core challenge behind these drawbacks: the LM-logical discrepancy featuring the difference between language modeling probabilities and logical probabilities.
  arXiv  Detail & Related papers  (2023-05-29T19:48:37Z)
• Adversarial Retriever-Ranker for dense text retrieval [51.87158529880056]
  We present Adversarial Retriever-Ranker (AR2), which consists of a dual-encoder retriever plus a cross-encoder ranker. AR2 consistently and significantly outperforms existing dense retriever methods. This includes the improvements on Natural Questions R@5 to 77.9%(+2.1%), TriviaQA R@5 to 78.2%(+1.4), and MS-MARCO MRR@10 to 39.5%(+1.3%)
  arXiv  Detail & Related papers  (2021-10-07T16:41:15Z)

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.