GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Long, Meixiu, Sun, Duolin, Yang, Dan, Jiao, Yihan, Liu, Lei, Wang, Jiahai, Hu, BinBin, Shen, Yue, Feng, Jie, Tan, Zhehao, Wang, Junjie, Zhong, Lianzhen, Wang, Jian, Wei, Peng, Gu, Jinjie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910178491760640
author Long, Meixiu
Sun, Duolin
Yang, Dan
Jiao, Yihan
Liu, Lei
Wang, Jiahai
Hu, BinBin
Shen, Yue
Feng, Jie
Tan, Zhehao
Wang, Junjie
Zhong, Lianzhen
Wang, Jian
Wei, Peng
Gu, Jinjie
author_facet Long, Meixiu
Sun, Duolin
Yang, Dan
Jiao, Yihan
Liu, Lei
Wang, Jiahai
Hu, BinBin
Shen, Yue
Feng, Jie
Tan, Zhehao
Wang, Junjie
Zhong, Lianzhen
Wang, Jian
Wei, Peng
Gu, Jinjie
contents Large Language Models (LLMs) have emerged as powerful tools for passage reranking in information retrieval, leveraging their superior reasoning capabilities to address the limitations of conventional models on complex queries. However, current LLM-based reranking paradigms are fundamentally constrained by an efficiency-accuracy trade-off: (1) pointwise methods are efficient but ignore inter-document comparison, yielding suboptimal accuracy; (2) listwise methods capture global context but suffer from context-window constraints and prohibitive inference latency. To address these issues, we propose GroupRank, a novel paradigm that balances flexibility and context awareness. To unlock the full potential of groupwise reranking, we propose an answer-free data synthesis pipeline that fuses local pointwise signals with global listwise rankings. These samples facilitate supervised fine-tuning and reinforcement learning, with the latter guided by a specialized group-ranking reward comprising ranking-utility and group-alignment. These complementary components synergistically optimize document ordering and score calibration to reflect intrinsic query-document relevance. Experimental results show GroupRank achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED, while delivering a 6.4$\times$ inference speedup.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11653
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs
Long, Meixiu
Sun, Duolin
Yang, Dan
Jiao, Yihan
Liu, Lei
Wang, Jiahai
Hu, BinBin
Shen, Yue
Feng, Jie
Tan, Zhehao
Wang, Junjie
Zhong, Lianzhen
Wang, Jian
Wei, Peng
Gu, Jinjie
Information Retrieval
Artificial Intelligence
Machine Learning
Large Language Models (LLMs) have emerged as powerful tools for passage reranking in information retrieval, leveraging their superior reasoning capabilities to address the limitations of conventional models on complex queries. However, current LLM-based reranking paradigms are fundamentally constrained by an efficiency-accuracy trade-off: (1) pointwise methods are efficient but ignore inter-document comparison, yielding suboptimal accuracy; (2) listwise methods capture global context but suffer from context-window constraints and prohibitive inference latency. To address these issues, we propose GroupRank, a novel paradigm that balances flexibility and context awareness. To unlock the full potential of groupwise reranking, we propose an answer-free data synthesis pipeline that fuses local pointwise signals with global listwise rankings. These samples facilitate supervised fine-tuning and reinforcement learning, with the latter guided by a specialized group-ranking reward comprising ranking-utility and group-alignment. These complementary components synergistically optimize document ordering and score calibration to reflect intrinsic query-document relevance. Experimental results show GroupRank achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED, while delivering a 6.4$\times$ inference speedup.
title GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs
topic Information Retrieval
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2511.11653