English

Evaluating Hydro-Science and Engineering Knowledge of Large Language Models

Computation and Language 2025-12-04 v1

Abstract

Hydro-Science and Engineering (Hydro-SE) is a critical and irreplaceable domain that secures human water supply, generates clean hydropower energy, and mitigates flood and drought disasters. Featuring multiple engineering objectives, Hydro-SE is an inherently interdisciplinary domain that integrates scientific knowledge with engineering expertise. This integration necessitates extensive expert collaboration in decision-making, which poses difficulties for intelligence. With the rapid advancement of large language models (LLMs), their potential application in the Hydro-SE domain is being increasingly explored. However, the knowledge and application abilities of LLMs in Hydro-SE have not been sufficiently evaluated. To address this issue, we propose the Hydro-SE LLM evaluation benchmark (Hydro-SE Bench), which contains 4,000 multiple-choice questions. Hydro-SE Bench covers nine subfields and enables evaluation of LLMs in aspects of basic conceptual knowledge, engineering application ability, and reasoning and calculation ability. The evaluation results on Hydro-SE Bench show that the accuracy values vary among 0.74 to 0.80 for commercial LLMs, and among 0.41 to 0.68 for small-parameter LLMs. While LLMs perform well in subfields closely related to natural and physical sciences, they struggle with domain-specific knowledge such as industry standards and hydraulic structures. Model scaling mainly improves reasoning and calculation abilities, but there is still great potential for LLMs to better handle problems in practical engineering application. This study highlights the strengths and weaknesses of LLMs for Hydro-SE tasks, providing model developers with clear training targets and Hydro-SE researchers with practical guidance for applying LLMs.

Keywords

Cite

@article{arxiv.2512.03672,
  title  = {Evaluating Hydro-Science and Engineering Knowledge of Large Language Models},
  author = {Shiruo Hu and Wenbo Shan and Yingjia Li and Zhiqi Wan and Xinpeng Yu and Yunjia Qi and Haotian Xia and Yang Xiao and Dingxiao Liu and Jiaru Wang and Chenxu Gong and Ruixi Zhang and Shuyue Wu and Shibo Cui and Chee Hui Lai and Wei Luo and Yubin He and Bin Xu and Jianshi Zhao},
  journal= {arXiv preprint arXiv:2512.03672},
  year   = {2025}
}

Comments

Hydro-SE Bench sets a new benchmark for the evaluation of LLMs in the Hydro-Science and Engineering domain, with its code and data available at \url{https://github.com/sheishijun/Hydro-SE-Bench}

R2 v1 2026-07-01T08:07:31.391Z