Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation

Changle Qu, Sunhao Dai, Hengyi Cai, Yiyang Cheng, Jun Xu, Shuaiqiang Wang, Dawei Yin


Abstract
Retrieval-augmented generation (RAG) has proven effective in enhancing the knowledge coverage of large language models (LLMs) and mitigating hallucinations by incorporating external retrieved documents. However, documents deemed relevant by the retriever are not necessarily helpful for answer generation, and including misleading information can even degrade performance. Existing efforts to estimate document utility often rely on the downstream generation performance, which conflates the influence of external documents with the intrinsic knowledge of the LLM, thereby obscuring the actual contribution of the retrieved content. To address this, this paper proposes Uplit-RAG, a uplift-driven knowledge preference alignment framework for RAG. Specifically, we first propose an uplift-based definition of document utility that quantifies each document’s marginal benefit over the LLM’s internal knowledge. We then optimize the reranker with three alignment objectives to identify and prioritize documents based on their uplift. This enables dynamic selection of documents that address the LLM’s knowledge gaps, going beyond fixed top-k selection, while reducing reference redundancy and the computational overhead of the LLM’s input. Extensive experiments demonstrate the effectiveness of Uplift-RAG.
Anthology ID:
2025.findings-emnlp.511
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9632–9644
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.511/
DOI:
Bibkey:
Cite (ACL):
Changle Qu, Sunhao Dai, Hengyi Cai, Yiyang Cheng, Jun Xu, Shuaiqiang Wang, and Dawei Yin. 2025. Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 9632–9644, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation (Qu et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.511.pdf
Checklist:
 2025.findings-emnlp.511.checklist.pdf