RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents

TL;DR

This paper introduces the RAH framework, leveraging LLM agents to create a human-centered recommendation system that improves personalization, reduces bias, and enhances user satisfaction across multiple domains.

Contribution

It presents an innovative human-centered recommendation framework utilizing LLM agents and a reflection mechanism, addressing key challenges like bias, privacy, and cold-start problems.

Findings

Effective in reducing human burden in recommendations

Mitigates biases and improves user control

Enhances personalization across domains

Abstract

The rapid evolution of the web has led to an exponential growth in content. Recommender systems play a crucial role in Human-Computer Interaction (HCI) by tailoring content based on individual preferences. Despite their importance, challenges persist in balancing recommendation accuracy with user satisfaction, addressing biases while preserving user privacy, and solving cold-start problems in cross-domain situations. This research argues that addressing these issues is not solely the recommender systems' responsibility, and a human-centered approach is vital. We introduce the RAH Recommender system, Assistant, and Human) framework, an innovative solution with LLM-based agents such as Perceive, Learn, Act, Critic, and Reflect, emphasizing the alignment with user personalities. The framework utilizes the Learn-Act-Critic loop and a reflection mechanism for improving user alignment. Using the real-world data, our experiments demonstrate the RAH framework's efficacy in various recommendation domains, from reducing human burden to mitigating biases and enhancing user control. Notably, our contributions provide a human-centered recommendation framework that partners effectively with various recommendation models.