arXiv subjects

Yonghao Wu

Publications and source records attributed to Yonghao Wu.

4 recordsLinked to original sources

arXiv2025

Exploring the Potential and Limitations of Large Language Models for Novice Program Fault Localization

Novice programmers often face challenges in fault localization due to their limited experience and understanding of programming syntax and logic. Traditional methods like Spectrum-Based Fault Localization (SBFL) and Mutation-Based Fault Localization (MBFL) help identify faults but often lack the ability to understand code context, making them less effective for beginners. In recent years, Large Language Models (LLMs) have shown promise in overcoming these limitations by utilizing their ability to understand program syntax and semantics. LLM-based fault localization provides more accurate and context-aware results than traditional techniques. This study evaluates six closed-source and seven open-source LLMs using the Codeflaws, Condefects, and BugT datasets, with BugT being a newly constructed dataset specifically designed to mitigate data leakage concerns. Advanced models with reasoning capabilities, such as OpenAI o3 and DeepSeekR1, achieve superior accuracy with minimal reliance on prompt engineering. In contrast, models without reasoning capabilities, like GPT-4, require carefully designed prompts to maintain performance. While LLMs perform well in simple fault localization, their accuracy decreases as problem difficulty increases, though top models maintain robust performance in the BugT dataset. Over-reasoning is another challenge, where some models generate excessive explanations that hinder fault localization clarity. Additionally, the computational cost of deploying LLMs remains a significant barrier for real-time debugging. LLM's explanations demonstrate significant value for novice programmer assistance, with one-year experience participants consistently rating them highly. Our findings demonstrate the potential of LLMs to improve debugging efficiency while stressing the need for further refinement in their reasoning and computational efficiency for practical adoption.

cs.SE↗

arXiv2025

Visual-Neural-Inspired Image Inpainting for Specific Objects-of-Interest Imaging

Conventional image inpainting techniques typically process entire images, which often leads to computational inefficiency and susceptibility to information redundancy, particularly in occluded or cluttered scenes. Inspired by cortical processing mechanisms, this study introduces a novel framework termed "Specific Object-of-Interest Imaging" (SIOI) to overcome these limitations. The proposed approach first extracts and encodes object-level representations from complex scenes, producing structural and semantic priors that can be seamlessly integrated into existing inpainting pipelines. Extensive evaluations on dedicated object datasets--Teapot, Elephant, Giraffe, and Zebra--demonstrate that models incorporating SIOI consistently outperform those without it across key metrics including SSIM, PSNR, MAE, and LPIPS. The framework also exhibits strong robustness under challenging conditions such as low illumination, high noise, multiple object occlusions, and motion blur. Furthermore, theoretical analysis grounded in cognitive neuroscience reveals meaningful connections between the "object-first" perceptual mechanism and dynamic feature modulation in visual cortical areas (V1-V4). By significantly enhancing object consistency and semantic coherence across diverse inpainting models, this work not only advances efficient and target-aware image restoration but also fosters interdisciplinary convergence between brain-inspired computation and cutting-edge inpainting technologies.

nlin.PS↗

arXiv2023

ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair

With the growing interest on Large Language Models (LLMs) for fault localization and program repair, ensuring the integrity and generalizability of the LLM-based methods becomes paramount. The code in existing widely-adopted benchmarks for these tasks was written before the the bloom of LLMs and may be included in the training data of existing popular LLMs, thereby suffering from the threat of data leakage, leading to misleadingly optimistic performance metrics. To address this issue, we introduce "ConDefects", a novel dataset of real faults meticulously curated to eliminate such overlap. ConDefects contains 1,254 Java faulty programs and 1,625 Python faulty programs. All these programs are sourced from the online competition platform AtCoder and were produced between October 2021 and September 2023. We pair each fault with fault locations and the corresponding repaired code versions, making it tailored for in fault localization and program repair related research. We also provide interfaces for selecting subsets based on different time windows and coding task difficulties. While inspired by LLM-based tasks, ConDefects can be adopted for benchmarking ALL types of fault localization and program repair methods. The dataset is publicly available, and a demo video can be found at https://www.youtube.com/watch?v=22j15Hj5ONk.

cs.SE↗

arXiv2023

Large Language Models in Fault Localisation

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.

cs.SE↗