cs.CLFeb 23, 2026

ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting

Authors: Yuxing Tian, Fengran Mo, Weixu Zhang, Yiyan Qi, Jian-Yun Nie

Organizations: University of Montreal · McGill University & MILA · International Digital Economy Academy

Abstract

The strong capabilities of recent Large Language Models (LLMs) have made them highly effective for zero-shot re-ranking task. Attention-based re-ranking methods, which derive relevance scores directly from attention weights, offer an efficient and interpretable alternative to generation-based re-ranking methods. However, they still face two major limitations. First, attention signals are highly concentrated a small subset of tokens within a few documents, making others indistinguishable. Second, attention often overemphasizes phrases lexically similar to the query, yielding biased rankings that irrelevant documents with mere lexical resemblance are regarded as relevant. In this paper, we propose ReAttn, a post-hoc re-weighting strategy for attention-based re-ranking methods. It first compute the cross-document IDF weighting to down-weight attention on query-overlapping tokens that frequently appear across the candidate documents, reducing lexical bias and emphasizing distinctive terms. It then employs entropy-based regularization to mitigate over-concentrated attention, encouraging a more balanced distribution across informative tokens. Both adjustments operate directly on existing attention weights without additional training or supervision. Extensive experiments demonstrate the effectiveness of our method.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models

    Apr 27, 2026Yuxing Tian, Fengran Mo, Zhiqi Huang +2Attention Head AnalysisLearning to Rank

  2. HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads

    Apr 19, 2026Juyuan Wang, Chenxing Wang, Yuchen Fang +8Attention Head AnalysisSelf-Attention

  3. The Emergence of Relevance Through Axiomatic Attention Patterns During LoRA Fine-Tuning

    Aug 24, 2026Matthew Perlman, Atharva Nijasure, James AllanLLM RerankingInformation Retrieval