Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
This addresses the need for personalized AI alignment for users with conflicting preferences, though it is incremental as it builds on existing RLHF and MORL methods.
The paper tackles the problem of aligning large language models with diverse individual preferences rather than aggregate ones, achieving personalized alignment by decomposing preferences into user-defined dimensions and combining them via post-hoc parameter merging.
While Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with general, aggregate human preferences, it is suboptimal for learning diverse, individual perspectives. In this work, we study Reinforcement Learning from Personalized Human Feedback (RLPHF) problem, wherein LLMs are aligned to multiple (sometimes conflicting) preferences by modeling alignment as a Multi-Objective Reinforcement Learning (MORL) problem. Compared to strong single-objective baselines, we show that we can achieve personalized alignment by decomposing preferences into multiple dimensions. These dimensions are defined based on personalizations that are declared as desirable by the user. In this work, we show that they can be efficiently trained independently in a distributed manner and combined effectively post-hoc through parameter merging. The code is available at https://github.com/joeljang/RLPHF.