基于语义熵反馈强化学习的大语言模型事实性幻觉缓解
顾滢双, 桂韬, 张奇
Mitigating Factuality Hallucination in LLM with Semantic Entropy based Reinforcement Learning and Multi-Agent Collaboration
GU Yingshuang , GUI Tao , ZHANG Qi
计算机工程
.
0, (): 0
-0
.
DOI: 10.19678/j.issn.1000-3428.0252253