Iterative Semantic Reasoning from Individual to Group Interests for Generative Recommendation with LLMs

Researchers propose an Iterative Semantic Reasoning Framework (ISRF) that uses large language models to improve recommendation systems by bridging explicit individual user interests with implicit group interests. The framework employs multi-step bidirectional reasoning and iterative optimization to achieve better user interest modeling than existing methods.

• →New ISRF framework combines LLMs with semantic reasoning to enhance recommendation system accuracy.
• →The approach bridges individual explicit interests with group implicit interests through three-step process.
• →Method uses bidirectional reasoning over item attributes and similarity-based user graphs.
• →Iterative batch optimization ensures consistent and progressive interest reasoning.
• →Testing on Sports, Beauty, and Toys datasets shows superior performance over existing baselines.