GOT4Rec leverages the "Graph of Thoughts" (GoT) prompting strategy within Large Language Models (LLMs) to significantly improve sequential recommendation accuracy by effectively capturing and integrating short-term, long-term, and collaborative user preferences.
The paper introduces DARec, a novel sequential recommendation model that leverages the power of large language models (LLMs) while addressing their limitations in capturing intra-item relations and long-term collaborative knowledge.