Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation

Guanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang, Ji-Rong Wen, Zhicheng Dou

Track: Search and retrieval-augmented AI

Keywords: Retrieval-Augmented Generation, Large Language Models, Preference Alignment

TL;DR: We reveal the inherent preference gaps between RAG components and further propose DPA-RAG, a universal framework to align diverse knowledge preferences within RAG systems through dual alignment methods.

Abstract: Retrieval-augmented generation (RAG) has demonstrated effectiveness in mitigating the hallucination problem of large language models (LLMs). However, the difficulty of aligning the retriever with the diverse LLMs' knowledge preferences inevitably poses an inevitable challenge in developing a reliable RAG system. To address this issue, we propose DPA-RAG, a universal framework designed to align diverse knowledge preferences within RAG systems. Specifically, we initially introduce a preference knowledge construction pipline and incorporate five novel query augmentation strategies to alleviate preference data scarcity. Based on preference data, DPA-RAG accomplishes both external and internal preference alignment: 1) It jointly integrate pair-wise, point-wise, and contrastive preference alignment abilities into the reranker, achieving external preference alignment among RAG components. 2) It further introduces a pre-aligned stage before vanilla Supervised Fine-tuning (SFT), enabling LLMs to implicitly capture knowledge aligned with their reasoning preferences, achieving LLMs' internal alignment. Experimental results across four knowledge-intensive QA datasets demonstrate that DPA-RAG outperforms all baselines and seamlessly integrates both black-box and open-sourced LLM readers. Further qualitative analysis and discussions also provide empirical guidance for achieving reliable RAG systems.

Submission Number: 2226