Shifting from Ranking to Set Selection for Retrieval Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Dahyun, Jo, Yongrae, Park, Haeju, Lee, Moontae
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912473342279680
author Lee, Dahyun
Jo, Yongrae
Park, Haeju
Lee, Moontae
author_facet Lee, Dahyun
Jo, Yongrae
Park, Haeju
Lee, Moontae
contents Retrieval in Retrieval-Augmented Generation(RAG) must ensure that retrieved passages are not only individually relevant but also collectively form a comprehensive set. Existing approaches primarily rerank top-k passages based on their individual relevance, often failing to meet the information needs of complex queries in multi-hop question answering. In this work, we propose a set-wise passage selection approach and introduce SETR, which explicitly identifies the information requirements of a query through Chain-of-Thought reasoning and selects an optimal set of passages that collectively satisfy those requirements. Experiments on multi-hop RAG benchmarks show that SETR outperforms both proprietary LLM-based rerankers and open-source baselines in terms of answer correctness and retrieval quality, providing an effective and efficient alternative to traditional rerankers in RAG systems. The code is available at https://github.com/LGAI-Research/SetR
format Preprint
id arxiv_https___arxiv_org_abs_2507_06838
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Shifting from Ranking to Set Selection for Retrieval Augmented Generation
Lee, Dahyun
Jo, Yongrae
Park, Haeju
Lee, Moontae
Computation and Language
Information Retrieval
Retrieval in Retrieval-Augmented Generation(RAG) must ensure that retrieved passages are not only individually relevant but also collectively form a comprehensive set. Existing approaches primarily rerank top-k passages based on their individual relevance, often failing to meet the information needs of complex queries in multi-hop question answering. In this work, we propose a set-wise passage selection approach and introduce SETR, which explicitly identifies the information requirements of a query through Chain-of-Thought reasoning and selects an optimal set of passages that collectively satisfy those requirements. Experiments on multi-hop RAG benchmarks show that SETR outperforms both proprietary LLM-based rerankers and open-source baselines in terms of answer correctness and retrieval quality, providing an effective and efficient alternative to traditional rerankers in RAG systems. The code is available at https://github.com/LGAI-Research/SetR
title Shifting from Ranking to Set Selection for Retrieval Augmented Generation
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2507.06838