Make Large Language Model a Better Ranker

The evolution of 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 LLMs. While some studies have delved into list-wise approaches, they fall short in ranking tasks. This shortfall is attributed to the misalignment between the objectives of ranking and language generation. To this end, this paper introduces the Language Model Framework with Aligned Listwise Ranking Objectives (ALRO). ALRO is designed to bridge the gap between the capabilities of LLMs and the nuanced requirements of ranking tasks within recommender systems. A key feature of ALRO is the introduction of soft lambda loss, an adaptation of lambda loss tailored to suit language generation tasks. Additionally, ALRO incorporates a permutation-sensitive learning mechanism that addresses position bias, a prevalent issue in generative models, without imposing additional computational burdens during inference. Our evaluative studies reveal that ALRO outperforms existing embedding-based recommendation methods and the existing LLM-based recommendation baselines, highlighting its efficacy.