Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenders

2025/10/10 by Ruixuan Sun, Sun, Ruixuan, Junyuan Wang +4
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Recommender Systems and Techniques

paper · pdf · doi:10.48550/arxiv.2510.08930

openalex publication_date 2025/10/10 · openalex created_date 2025/10/14 · openalex updated_date 2026/07/28

Abstract

Natural language-based user profiles in recommender systems have been explored for their interpretability and potential to help users scrutinize and refine their interests, thereby improving recommendation quality. Building on this foundation, we introduce a human-AI collaborative profile for a movie recommender system that presents editable personalized interest summaries of a user's movie history. Unlike static profiles, this design invites users to directly inspect, modify, and reflect on the system's inferences. In an eight-week online field deployment with 1775 active movie recommender users, we find persistent gaps between user-perceived and system-inferred interests, show how the profile encourages engagement and reflection, and identify design directions for leveraging imperfect AI-powered user profiles to stimulate more user intervention and build more transparent and trustworthy recommender experiences.

Citations

• LLM-based User Profile Management for Recommender System
• Recommending the right academic programs: An interest mining approach using BERTopic
• End-to-end Training for Recommendation with Language-based User Profiles
• MEGAnno+: A Human-LLM Collaborative Annotation System
• Language-Based User Profiles for Recommendation
• Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models
• A Survey on User Behavior Modeling in Recommender Systems
• PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement
• BERTopic: Neural topic modeling with a class-based TF-IDF procedure
• Explaining the user experience of recommender systems
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• On Generative Agents in Recommendation
• SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation
• Factual and Personalized Recommendations using Language Models and Reinforcement Learning
• Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems
• A survey on the impacts of recommender systems on users, items, and human-AI ecosystems