Evaluating Hydro-Science and Engineering Knowledge of Large Language Models
This provides practical guidance for Hydro-SE researchers applying LLMs and clear training targets for model developers, though it's an incremental contribution focused on evaluation rather than new capabilities.
The researchers tackled the problem of insufficient evaluation of large language models' knowledge and application abilities in Hydro-Science and Engineering by creating Hydro-SE Bench, a benchmark with 4,000 multiple-choice questions across nine subfields. Results showed commercial LLMs achieved 0.74-0.80 accuracy while small-parameter LLMs scored 0.41-0.68, with models performing well on science-related questions but struggling with domain-specific knowledge like industry standards.
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.