K-order Ranking Preference Optimization for Large Language Models

ACL ARR 2025 February Submission5160 Authors

Abstract:

To adapt Large Language Models (LLMs) to ranking tasks, existing list-wise methods, represented by list-wise Direct Preference Optimization (DPO), focus on optimizing partial-order or full-order list ranking consistency for LLMs to enhance their ranking abilities.
However, we argue that optimizing top-K ranking consistency could be more appropriate for real-world applications. There are two main reasons: (1) users are typically concerned with only the top-K results, making top-K ranking more important, and (2) tail items often lack precise feedback, making top-K ranking more reliable. Based on this, we propose $\textit{\textbf{K}}$-order Ranking $\textbf{P}$reference $\textbf{O}$ptimization (KPO) by extending the DPO’s Plackett-Luce model to accommodate top-K rankings. Additionally, recognizing that the number of important items can vary across queries, we extend KPO to dynamically determine appropriate $K$ for different samples and introduce a curriculum learning strategy to boost training efficiency. Extensive experiments demonstrate the effectiveness of KPO, highlighting its high sample efficiency and robustness to noise. The code is available at https://anonymous.4open.science/r/KPO-BEAF.

Paper Type: Long

Research Area: Information Retrieval and Text Mining

Research Area Keywords: re-ranking

Languages Studied: English

Submission Number: 5160