Poster · Sydney
BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation
- When
- Thu 10 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 6
- Authors
- Ning Li, Zixuan Guo, Yan Xu, Wenbo Fei, Yifan Niu, Chang Luo, Yasheng Wang, Weiwen Liu, Yong Yu, Weinan Zhang
- Organisations
- Shanghai Jiao Tong University, Tencent, Huawei, Hong Kong University of Science and Technology (Guangzhou), University of Edinburgh
- QRS classification
- Reinforcement learning, Language models, Safety, fairness and privacy