Make Large Language Model a Better Ranker

arXiv:2403.19181v1 Announce Type: cross
Abstract: The evolution of Large Language Models (LLMs) has significantly enhanced capabilities across various fields, leading to a paradigm shift in how Recommender Systems (RSs) are conceptualized and developed. However, existing research primarily focuses on point-wise and pair-wise recommendation paradigms. These approaches prove inefficient in LLM-based recommenders due to the high computational cost of utilizing Large Language Models. While some studies have delved into list-wise approaches, they fall short in ranking tasks. This shortfall is attributed …

abstract arxiv capabilities cs.cl cs.ir cs.lg evolution fields however language language model language models large language large language model large language models llm llms paradigm prove recommendation recommenders recommender systems research rss shift systems type wise