一作ACL 2026Findings· Findings of ACL
R esearch B ench: Benchmarking LLM s in Scientific Discovery via Inspiration-Based Task Decomposition
Yujie Liu · Zonglin Yang · Tong Xie · Jinjie Ni · Ben Gao · Yuqiang Li · SHIXIANG TANG · Wanli Ouyang · Erik Cambria · Dongzhan Zhou
摘要
Large language models (LLMs) have shown potential in assisting scientific research, yet their ability to discover high-quality research hypotheses remains unexamined due to the lack of a dedicated benchmark. To address this gap, we introduce the first large-scale benchmark for evaluating LLMs on...