Saved in:
Bibliographic Details
Main Authors: Song, Zhipeng, Zhou, Yizhi, Kong, Xiangyu, Jiao, Jiulong, Ye, Xuezhou, Gao, Chunqi, Shi, Xueqing, Zhou, Yuhang, Qi, Heng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.04495
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909016806916096
author Song, Zhipeng
Zhou, Yizhi
Kong, Xiangyu
Jiao, Jiulong
Ye, Xuezhou
Gao, Chunqi
Shi, Xueqing
Zhou, Yuhang
Qi, Heng
author_facet Song, Zhipeng
Zhou, Yizhi
Kong, Xiangyu
Jiao, Jiulong
Ye, Xuezhou
Gao, Chunqi
Shi, Xueqing
Zhou, Yuhang
Qi, Heng
contents Retrieval-Augmented Generation (RAG) depends on document ranking to provide useful evidence for generation, but conventional reranking methods mainly optimize query-document relevance rather than generation usefulness. A relevant document may still introduce noise, while a lower-ranked document may better reduce the generator's uncertainty. We propose CAR (Confidence-Aware Reranking), a query-guided, training-free, and plug-and-play reranking framework that uses generator confidence change as a document usefulness signal. CAR estimates confidence through the semantic consistency of multiple sampled answers under query-only and query-document conditions. Documents that significantly increase confidence are promoted, those that decrease confidence are demoted, and uncertain cases preserve the baseline order, while a query-level gate avoids unnecessary intervention on already confident queries. Experiments on four BEIR datasets show that CAR consistently improves NDCG@5 across sparse and dense retrievers, LLM-based and supervised rerankers, and four LLM backbones. Notably, CAR improves the YesNo reranker by 25.4 percent on average under Contriever retrieval, and its ranking gains strongly correlate with downstream generation F1 improvements, achieving Spearman rho = 0.964.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04495
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation
Song, Zhipeng
Zhou, Yizhi
Kong, Xiangyu
Jiao, Jiulong
Ye, Xuezhou
Gao, Chunqi
Shi, Xueqing
Zhou, Yuhang
Qi, Heng
Computation and Language
Artificial Intelligence
Retrieval-Augmented Generation (RAG) depends on document ranking to provide useful evidence for generation, but conventional reranking methods mainly optimize query-document relevance rather than generation usefulness. A relevant document may still introduce noise, while a lower-ranked document may better reduce the generator's uncertainty. We propose CAR (Confidence-Aware Reranking), a query-guided, training-free, and plug-and-play reranking framework that uses generator confidence change as a document usefulness signal. CAR estimates confidence through the semantic consistency of multiple sampled answers under query-only and query-document conditions. Documents that significantly increase confidence are promoted, those that decrease confidence are demoted, and uncertain cases preserve the baseline order, while a query-level gate avoids unnecessary intervention on already confident queries. Experiments on four BEIR datasets show that CAR consistently improves NDCG@5 across sparse and dense retrievers, LLM-based and supervised rerankers, and four LLM backbones. Notably, CAR improves the YesNo reranker by 25.4 percent on average under Contriever retrieval, and its ranking gains strongly correlate with downstream generation F1 improvements, achieving Spearman rho = 0.964.
title CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2605.04495