作者位次 #3/8ACL 2026Findings· Findings of ACL
M ulti F ile T est: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms
Yibo Wang · Congying Xia · Wenting Zhao · Jiangshu Du · Chunyu Miao · Zhongfen Deng · Philip S. Yu · Chen Xing
摘要
Unit test generation has become a promising and important use case for Large Language Models (LLMs). However, existing evaluation benchmarks for LLM unit test generation primarily focus on function- or class-level code (single-file) rather than on more practical, challenging multi-file codebases....