Sparks of Artificial General Recommender (AGR): Early Experiments with ChatGPT
This work explores a general-purpose recommendation system for users across domains, but it is incremental as it builds on existing LLMs like ChatGPT.
This study investigates the feasibility of an Artificial General Recommender (AGR) using ChatGPT, proposing ten principles and testing protocols, and finds that ChatGPT shows potential as an AGR but with limitations.
This study investigates the feasibility of developing an Artificial General Recommender (AGR), facilitated by recent advancements in Large Language Models (LLMs). An AGR comprises both conversationality and universality to engage in natural dialogues and generate recommendations across various domains. We propose ten fundamental principles that an AGR should adhere to, each with its corresponding testing protocols. We proceed to assess whether ChatGPT, a sophisticated LLM, can comply with the proposed principles by engaging in recommendation-oriented dialogues with the model while observing its behavior. Our findings demonstrate the potential for ChatGPT to serve as an AGR, though several limitations and areas for improvement are identified.