REVIEW 2 cited by
Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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. Our code is publicly available at https://github.com/dongguanting/DPA-RAG.
Forward citations
Cited by 2 Pith papers
-
Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation
Omni-RAG, a query-rewriting and decomposition pipeline on top of standard retrieval and reranking, achieved rank 2 in the SIGIR 2025 LiveRAG Challenge.
-
Optimizing Web-Based AI Query Retrieval with GPT Integration in LangChain A CoT-Enhanced Prompt Engineering Approach
A LangChain plus GPT-4o retrieval pipeline with chain-of-thought prompting is claimed to beat GPT-4o on two QA benchmarks, but the headline numbers are inconsistent with the stated dataset size.
Discussion (0). Sign in to comment.