RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational Recommenders

Abstract: Conversational recommender systems (CRS) based on LLMs need to constantly be aligned to the user preferences to provide satisfying and context-relevant item recommendations. The traditional supervised fine-tuning cannot capture the implicit feedback signal, e.g., dwell time, sentiment polarity, or engagement patterns. In this paper, we share a fine-tuning solution using human feedback reinforcement learning (RLHF) to maximize implied user feedback (IUF) in a multi-turn recommendation context. We specify a reward model $R_{\phi}$ learnt on weakly-labelled engagement information and maximize user-centric utility by optimizing the foundational LLM M_{\theta} through a proximal policy optimization (PPO) approach. The architecture models conversational state transitions $s_t \to a_t \to s_{t +1}$, where the action $a_t$ is associated with LLM-generated item suggestions only on condition of conversation history in the past. The evaluation across synthetic and real-world datasets (e.g.REDIAL, OpenDialKG) demonstrates that our RLHF-fine-tuned models can perform better in terms of top-$k$ recommendation accuracy, coherence, and user satisfaction compared to (arrow-zero-cmwrquca-teja-falset ensuite 2Round group-deca States penalty give up This paper shows that implicit signal alignment can be efficient in achieving scalable and user-adaptive design of CRS.