作者位次 #5/12ACL 2026Findings· Findings of ACL
E ngi B ench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving
Xiyuan Zhou · Xinlei Wang · Yirui He · Ruixi Zou · Yang Wu · Yuheng Cheng · Yulu Xie · Wenxuan Liu · Huan Zhao · Yan Xu · Jinjin Gu · Junhua Zhao
摘要
Large language models (LLMs) have shown strong performance on mathematical reasoning under well-defined conditions. However, real-world engineering problems involve uncertainty, context, and open-ended settings that extend beyond symbolic computation. Existing benchmarks largely focus on well-def...