作者位次 #4/9ACL 2026Poster· Natural Language Processing
DPW riter: Reinforcement Learning with Diverse Planning Branching for Creative Writing
Qian Cao · Yahui Liu · Wei BI · Yi Zhao · Ruihua Song · Xiting Wang · Ruiming Tang (Huawei Noah' · Guorui Zhou · Han Li
摘要
Reinforcement learning (RL)-based enhancement of large language models (LLMs) often leads to reduced output diversity, undermining their utility in open-ended tasks like creative writing. Current methods lack explicit mechanisms for guiding diverse exploration and instead prioritize optimization...