English
Related papers

Related papers: Mokav: Execution-driven Differential Testing with …

200 papers

To solve complex tasks, large language models (LLMs) often require multiple rounds of interactions with the user, sometimes assisted by external tools. However, current evaluation protocols often emphasize benchmark performance with…

Computation and Language · Computer Science 2024-03-13 Xingyao Wang , Zihan Wang , Jiateng Liu , Yangyi Chen , Lifan Yuan , Hao Peng , Heng Ji

Code documentation can, if written precisely, help developers better understand the code they accompany. However, unlike code, code documentation cannot be automatically verified via execution, potentially leading to inconsistencies between…

Software Engineering · Computer Science 2025-02-06 Hyeonseok Lee , Gabin An , Shin Yoo

Software testing is an essential part of the software development cycle to improve the code quality. Typically, a unit test consists of a test prefix and a test oracle which captures the developer's intended behaviour. A known limitation of…

Software Engineering · Computer Science 2024-10-29 Michael Konstantinou , Renzo Degiovanni , Mike Papadakis

Recently, there has been increasing interest in using Large Language Models (LLMs) to construct complex multi-agent systems to perform tasks such as compiling literature reviews, drafting consumer reports, and planning vacations. Many tools…

Computation and Language · Computer Science 2024-11-06 Andrew Zhu , Liam Dugan , Chris Callison-Burch

Requirements Engineering (RE) is essential for developing complex and regulated software projects. Given the challenges in transforming stakeholder inputs into consistent software designs, Qualitative Data Analysis (QDA) provides a…

Software Engineering · Computer Science 2025-04-29 Syed Tauhid Ullah Shah , Mohamad Hussein , Ann Barcomb , Mohammad Moshirpour

Code large language models (LLMs) have shown remarkable advances in code understanding, completion, and generation tasks. Programming benchmarks, comprised of a selection of code challenges and corresponding test cases, serve as a standard…

Metamorphic testing (MT) has proven to be a successful solution to automating testing and addressing the oracle problem. However, it entails manually deriving metamorphic relations (MRs) and converting them into an executable form; these…

Software Engineering · Computer Science 2024-10-14 Seung Yeob Shin , Fabrizio Pastore , Domenico Bianculli , Alexandra Baicoianu

Testing is an integral part of the software development process. Yet, writing tests is time-consuming and therefore often neglected. Classical test generation tools such as EvoSuite generate behavioral test suites by optimizing for…

Software Engineering · Computer Science 2023-10-04 Nikitha Rao , Kush Jain , Uri Alon , Claire Le Goues , Vincent J. Hellendoorn

Code-documentation inconsistencies are common and undesirable: they can lead to developer misunderstandings and software defects. This paper introduces DocPrism, a multi-language, code-documentation inconsistency detection tool. DocPrism…

Software Engineering · Computer Science 2025-11-04 Xiaomeng Xu , Zahin Wahab , Reid Holmes , Caroline Lemieux

Self-Correction aims to enable large language models (LLMs) to self-verify and self-refine their initial responses without external feedback. However, LLMs often fail to effectively self-verify and generate correct feedback, further…

Computation and Language · Computer Science 2025-05-28 Xiaoshuai Song , Yanan Wu , Weixun Wang , Jiaheng Liu , Wenbo Su , Bo Zheng

Program verification relies on loop invariants, yet automatically discovering strong invariants remains a long-standing challenge. We investigate whether large language models (LLMs) can accelerate program verification by generating useful…

Programming Languages · Computer Science 2026-04-03 Anjiang Wei , Tianran Sun , Tarun Suresh , Haoze Wu , Ke Wang , Alex Aiken

While large language models (LLMs) have exhibited impressive instruction-following capabilities, it is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions. As a…

Computation and Language · Computer Science 2024-01-02 Yihan Chen , Benfeng Xu , Quan Wang , Yi Liu , Zhendong Mao

Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM with comprehensive performance yet ultimate efficiency.…

Large language models (LLMs) have become proficient at sophisticated code-generation tasks, yet remain ineffective at reliably detecting or avoiding code vulnerabilities. Does this deficiency stem from insufficient learning about code…

Cryptography and Security · Computer Science 2025-07-15 Weichen Yu , Ravi Mangal , Terry Zhuo , Matt Fredrikson , Corina S. Pasareanu

To evaluate large language models (LLMs) for code, research has used manually created unit test-based benchmarks. However, these tests are often inadequate, missing corner cases and other implementation-specific oddities. This work…

Software Engineering · Computer Science 2025-02-27 Miltiadis Allamanis , Pengcheng Yin

Large language models (LLMs) have recently achieved significant success across various application domains, garnering substantial attention from different communities. Unfortunately, even for the best LLM, many \textit{faults} still exist…

Software Engineering · Computer Science 2024-11-06 Qiang Hu , Jin Wen , Maxime Cordy , Yuheng Huang , Wei Ma , Xiaofei Xie , Lei Ma

Although large language models (LLMs) excel in text comprehension and generation, their performance on the Emotion-Cause Pair Extraction (ECPE) task, which requires reasoning ability, is often underperform smaller language model. The main…

Computation and Language · Computer Science 2025-07-22 Shiyi Mu , Yongkang Liu , Shi Feng , Xiaocui Yang , Daling Wang , Yifei Zhang

Large Language Models (LLM) show strong abilities in code generation, but their skill in creating efficient parallel programs is less studied. This paper explores how LLMs generate task-based parallel code from three kinds of input prompts:…

Programming Languages · Computer Science 2026-02-27 Linus Bantel , Moritz Strack , Alexander Strack , Dirk Pflüger

Large language models (LLMs) have made impressive progress in natural language processing. These models rely on proper human instructions (or prompts) to generate suitable responses. However, the potential of LLMs are not fully harnessed by…

Computation and Language · Computer Science 2023-10-24 Xinyu Hu , Pengfei Tang , Simiao Zuo , Zihan Wang , Bowen Song , Qiang Lou , Jian Jiao , Denis Charles

Unlike code completion, debugging requires localizing faults and applying targeted edits. We observe that frontier LLMs often regenerate correct but over-edited solutions during debugging. To evaluate how far LLMs are from precise…

Software Engineering · Computer Science 2026-05-19 Wang Bill Zhu , Miaosen Chai , Shangshang Wang , Yejia Liu , Song Bian , Honghua Dong , Willie Neiswanger , Robin Jia
‹ Prev 1 3 4 5 6 7 10 Next ›