English
Related papers

Related papers: TSSB-3M: Mining single statement bugs at massive s…

200 papers

Although Large Language Models (LLMs) have become capable reasoners, the problem of faithfulness persists: their reasoning can contain errors and omissions that are difficult to detect and that may obscure biases in model outputs. To…

Computation and Language · Computer Science 2025-09-30 Jixuan Leng , Cassandra A. Cohen , Zhixian Zhang , Chenyan Xiong , William W. Cohen

Python is a widely adopted programming language, valued for its simplicity and flexibility. However, its dynamic type system poses significant challenges for automated refactoring - an essential practice in software evolution aimed at…

Software Engineering · Computer Science 2025-11-20 Jonhnanthan Oliveira , Rohit Gheyi , Márcio Ribeiro , Alessandro Garcia

Large Language Models (LLMs) such as ChatGPT-4, Claude 3, and LLaMA 4 are increasingly embedded in software/application development, supporting tasks from code generation to debugging. Yet, their real-world effectiveness in detecting…

Software Engineering · Computer Science 2026-04-28 Akshay Mhatre , Noujoud Nader , Patrick Diehl , Deepti Gupta

Automated debugging techniques have the potential to reduce developer effort in debugging, and have matured enough to be adopted by industry. However, one critical issue with existing techniques is that, while developers want rationales for…

Software Engineering · Computer Science 2023-04-06 Sungmin Kang , Bei Chen , Shin Yoo , Jian-Guang Lou

Benchmarks play an important role in evaluating the efficiency and effectiveness of solutions to automate several phases of the software development lifecycle. Moreover, if well designed, they also serve us well as an important artifact to…

Software Engineering · Computer Science 2019-05-24 Thomas Durieux , Rui Abreu

This paper presents a large-scale study that investigates the bug resolution characteristics among popular Github projects written in different programming languages. We explore correlations but, of course, we cannot infer causation.…

Software Engineering · Computer Science 2020-01-07 Jie M. Zhang , Feng Li , Dan Hao , Meng Wang , Hao Tang , Lu Zhang , Mark Harman

Software auditing is an increasingly critical task in the era of rapid code generation. While LLM-based auditors have demonstrated strong potential, their effectiveness remains limited by misalignment with the highly complex,…

Software Engineering · Computer Science 2026-04-16 Jinyao Guo , Chengpeng Wang , Dominic Deluca , Jinjie Liu , Zhuo Zhang , Xiangyu Zhang

Large Language Models (LLMs) have demonstrated significant potential in automated software security, particularly in vulnerability detection. However, existing benchmarks primarily focus on isolated, single-vulnerability samples or…

Cryptography and Security · Computer Science 2025-12-30 Chinmay Pushkar , Sanchit Kabra , Dhruv Kumar , Jagat Sesh Challa

Gradual typing enables developers to annotate types of their own choosing, offering a flexible middle ground between no type annotations and a fully statically typed language. As more and more code bases get type-annotated, static type…

Software Engineering · Computer Science 2024-01-15 Yiu Wai Chow , Luca Di Grazia , Michael Pradel

Large Language models (LLMs) can be induced to solve non-trivial problems with "few-shot" prompts including illustrative problem-solution examples. Now if the few-shots also include "chain of thought" (CoT) explanations, which are of the…

Software Engineering · Computer Science 2023-08-21 Toufique Ahmed , Premkumar Devanbu

Software bugs claim approximately 50% of development time and cost the global economy billions of dollars. Once a bug is reported, the assigned developer attempts to identify and understand the source code responsible for the bug and then…

Software Engineering · Computer Science 2025-01-29 Parvez Mahbub , Ohiduzzaman Shuvo , Mohammad Masudur Rahman

Large Language Models (LLMs) are increasingly applied to automated software testing, yet their ability to generalize beyond memorized patterns and reason about natural language bug reports remains unclear. We present a systematic evaluation…

Software Engineering · Computer Science 2025-10-08 Irtaza Sajid Qureshi , Zhen Ming , Jiang

Although large language models (LLMs) have achieved remarkable performance across various tasks, they remain prone to errors. A key challenge is enabling them to self-correct. While prior research has relied on external tools or large…

Computation and Language · Computer Science 2025-03-12 Viktor Moskvoretskii , Chris Biemann , Irina Nikishina

Fault-detection, localization, and repair methods are vital to software quality; but it is difficult to evaluate their generality, applicability, and current effectiveness. Large, diverse, realistic datasets of durably-reproducible faults…

Large Language Models (LLMs) are increasingly deployed to resolve real-world GitHub issues. However, despite their potential, the specific failure modes of these models in complex repair tasks remain poorly understood. To characterize how…

Software Engineering · Computer Science 2026-05-13 Yanjie Jiang , Yian Huang , Guancheng Wang , Junjie Chen , Hui Liu , Lionel Briand

Bug reports are essential for developers to confirm software problems, investigate their causes, and validate fixes. Unfortunately, reports often miss important information or are written unclearly, which can cause delays, increased issue…

Software Engineering · Computer Science 2025-02-07 Junayed Mahmud , Antu Saha , Oscar Chaparro , Kevin Moran , Andrian Marcus

Software bugs significantly contribute to software cost and increase the risk of system malfunctioning. In recent years, many automated program-repair approaches have been proposed to automatically fix undesired program behavior. Despite of…

Software Engineering · Computer Science 2021-07-19 Dirk Beyer , Lars Grunske , Thomas Lemberger , Minxing Tang

Many techniques for automated program repair involve syntactic program transformations. Applying combinations of such transformations on faulty code yields fix candidates whose correctness must be determined. Exploring these combinations…

This study explores the potential of Large Language Models (LLMs) in automating the repair of C programs. We present a framework that integrates spectrum-based fault localization (SBFL), runtime feedback, and Chain-of-Thought-structured…

Software Engineering · Computer Science 2025-09-04 Mahdi Farzandway , Fatemeh Ghassemi