作者位次 #2/7ACL 2026Findings· Findings of ACL
S ci T ext2 E q: Assessing LLM s for Explainable Equation Generation for Scientific Creativity
Yifan Mo · Xiao Fu · Yue Su · Qingyu Meng · Koen Hindriks · Qingzhi Liu · Jiahuan Pei
摘要
This work investigates the ability of large language models (LLMs) to generate mathematical equations from scientific texts. Prior work faces challenges in unstructured grounding, multi-equation dependency, and human-aligned evaluation. To address this, we construct a dataset of AI research paper...