Multi-Objective Exploration and Preference Optimization via Mutual Information

arXiv:2607.01392v1 Announce Type: new Abstract: Aligning large language models with diverse and heterogeneous human values requires multi-objective alignment methods to effectively trade off conflicting preference dimensions. Current methods achieve this trade-off by training policies conditioned on preference vectors and leveraging online direct preference optimization. However, exploration uncertainty can cause the reward distributions of responses generated under different preference vectors ...