Large Language Models for Multi-Lingual Equivalent Mutant Detection: An Extended Empirical Study
2026-07-01 • Software Engineering
Software Engineering
AI summaryⓘ
The authors studied how large language models (LLMs) can help detect equivalent mutants—code changes that don’t affect a program’s behavior—in software testing. They tested these models on Java and C code, finding that LLMs performed better than traditional methods and worked efficiently. They also showed that fine-tuning LLMs helped them work well across different programming languages. This research suggests LLMs could improve a tricky part of software quality testing called mutation testing.
mutation testingequivalent mutantsequivalent mutant detection (EMD)large language models (LLMs)code embeddingsoftware qualitymachine learningcross-lingual generalizationcompiler infrastructurefine-tuning
Authors
Honglin Shu, Zhao Tian, Dong Wang, Junji Yu, Jiazhe Zhang, Xuejie Cao, Junjie Chen, Yasutaka Kamei
Abstract
Mutation testing is a powerful technique for ensuring software quality. However, the presence of equivalent mutants introduces unnecessary costs and biases, limiting its practical effectiveness. Although numerous equivalent mutant detection (EMD) methods have been proposed, they often face distinct challenges: pure-code analysis methods can be limited by their reliance on specific compiler infrastructures, while existing machine-learning approaches remain constrained by scarce training data and limited generalization to unseen mutants. Large language models (LLMs) have recently demonstrated remarkable performance across diverse code-related tasks by better capturing program semantics. Yet their potential for EMD remains largely unexplored, particularly in the multi-lingual context. This paper presents the first comprehensive empirical study on LLMs for EMD, using 3,302 Java and 1,088 C mutant pairs to benchmark against state-of-the-art methods, explore strategy variations, assess efficiency, and evaluate cross-lingual generalization. Experimental results show that LLM-based approaches achieve higher F1-scores than the evaluated traditional methods, with fine-tuned code embedding yielding the highest detection accuracy among the tested strategies. Moreover, LLM-based approaches strike a practical balance between effectiveness and efficiency with inference times comparable to existing machine-learning models. Importantly, fine-tuned LLMs demonstrate measurable generalization across programming languages. These findings establish LLMs as a viable and efficient approach for tackling the longstanding challenge of equivalent mutant detection, offering new directions for advancing mutation testing in practice.