RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents
This work addresses issues in recommender systems for users and developers by proposing a novel framework, though it appears incremental as it builds on existing methods with LLM agents.
The paper tackles challenges in recommender systems like balancing accuracy with user satisfaction, addressing biases, and solving cold-start problems by introducing the RAH framework, which uses LLM-based agents and a human-centered approach to improve user alignment and control in various recommendation domains.
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.