Improving LLM-powered Recommendations with Personalized Information
This addresses the issue of ineffective reasoning utilization in LLM-powered recommendations for users and developers, but appears incremental as it builds on existing CoT methods.
The paper tackles the problem of LLM-powered recommendations lacking explicit reasoning modeling by proposing CoT-Rec, a pipeline that integrates Chain-of-Thought processes for user preference and item perception analysis, showing potential for improvement in experimental results.
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.