Prometheus Chatbot: Knowledge Graph Collaborative Large Language Model for Computer Components Recommendation
This work addresses the problem of ambiguous natural language processing and entity linking in recommender systems for users seeking computer components, representing an incremental improvement in domain-specific applications.
The authors tackled the challenge of developing a knowledge graph-based recommender system that processes natural language inputs by creating Prometheus, a chatbot that integrates a knowledge graph with a large language model for computer component recommendations, achieving accurate decoding of user requests and personalized suggestions.
Knowledge graphs (KGs) are essential in applications such as network alignment, question-answering, and recommender systems (RSs) since they offer structured relational data that facilitate the inference of indirect relationships. However, the development of KG-based RSs capable of processing user inputs in natural language faces significant challenges. Firstly, natural language processing units must effectively handle the ambiguity and variability in human language to interpret user intents accurately. Secondly, the system must precisely identify and link entities, like product names, to their corresponding nodes in KGs. To overcome these challenges, supported by Lenovo, we developed a novel chatbot called "Prometheus," which integrates a KG with a large language model (LLM), specifically designed for recommending computer components. This chatbot can accurately decode user requests and deliver personalized recommendations derived from KGs, ensuring precise comprehension and response to their computer setup needs.