一作ACL 2026Poster· Natural Language Processing
E vo N arrator: Modeling Scientific Evolution for Feasible Hypothesis Generation
Xiaoying Le · Pengfei Qian · Yuanzhao Zhai · Xu Zhang · Qian Liu · Feng Dawei · Bo Ding
摘要
Scientific discovery evolution does not emerge in isolation but stems from the structural deepening and recombination of existing functionalities. However, current automated hypothesis generation methods, constrained by the statistical co-occurrence nature of Large Language Models (LLMs), lack pe...