The Era of Real-World Human Interaction: RL from User Conversations
This addresses scalable and personalized alignment for conversational AI models, though it builds incrementally on existing RL and personalization techniques.
The paper tackles the problem of aligning conversational models by learning directly from natural human interactions rather than pre-annotated expert feedback, introducing Reinforcement Learning from Human Interaction (RLHI) with two methods that outperform baselines in personalization and instruction-following on WildChat data.
We posit that to achieve continual model improvement and multifaceted alignment, future models must learn from natural human interaction. Current conversational models are aligned using pre-annotated, expert-generated human feedback. In this work, we introduce Reinforcement Learning from Human Interaction (RLHI), a paradigm that learns directly from in-the-wild user conversations. We develop two complementary methods: (1) RLHI with User-Guided Rewrites, which revises unsatisfactory model outputs based on users' natural-language follow-up responses, (2) RLHI with User-Based Rewards, which learns via a reward model conditioned on knowledge of the user's long-term interaction history (termed persona). Together, these methods link long-term user personas to turn-level preferences via persona-conditioned preference optimization. Trained on conversations derived from WildChat, both RLHI variants outperform strong baselines in personalization and instruction-following, and similar feedback enhances performance on reasoning benchmarks. These results suggest organic human interaction offers scalable, effective supervision for personalized alignment.