Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation

Understand

Aligning Large Language Models (LLMs) with recommendation tasks represents an emerging paradigm in recommendation domain, exhibiting promising performance overall.

• However, these aligned recommendation LLMs often struggle with complex scenarios due to limitations in the current alignment task formulation, which optimizes LLMs to directly generate user feedback without deliberation.
• To develop more reliable recommendation LLMs, we introduce a new \textit{Deliberative Recommendation} task, which enforces explicit reasoning about user preferences as an additional alignment objective.
• To address this task, we propose a \textit{Reasoning-powered Recommender} framework designed to enhance reasoning capabilities by leveraging verbalized user feedback in a step-wise manner.