Improving LLM-powered Recommendations with Personalized Information

TL;DR

This paper introduces CoT-Rec, a pipeline that enhances LLM-powered recommendations by integrating personalized user preferences and item perceptions through Chain-of-Thought processes, improving reasoning capabilities.

Contribution

The paper proposes a novel two-stage pipeline, CoT-Rec, that incorporates personalized information extraction and utilization to improve LLM-based recommendation systems.

Findings

CoT-Rec improves recommendation quality in experiments.

The approach effectively leverages LLM reasoning capabilities.

Implementation is publicly available for reproducibility.

Abstract

Due to the lack of explicit reasoning modeling, existing LLM-powered recommendations fail to leverage LLMs' reasoning capabilities effectively. In this paper, we propose a pipeline called CoT-Rec, which integrates two key Chain-of-Thought (CoT) processes -- user preference analysis and item perception analysis -- into LLM-powered recommendations, thereby enhancing the utilization of LLMs' reasoning abilities. CoT-Rec consists of two stages: (1) personalized information extraction, where user preferences and item perception are extracted, and (2) personalized information utilization, where this information is incorporated into the LLM-powered recommendation process. Experimental results demonstrate that CoT-Rec shows potential for improving LLM-powered recommendations. The implementation is publicly available at https://github.com/jhliu0807/CoT-Rec.