Paper Detail

Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking

Lijun Liu, Zhengzong Chen, Wenyan Li, Yuanyuan Zhao, Fei Huang

arxiv Score 18.8

Published 2026-09-17 · First seen 2026-09-21

General AI

Abstract

Reasoning-based reranking with Large Language Models (LLMs) has shown promising improvements in text ranking. However, current methods predominantly rely on a single reasoning trajectory, resulting in rankings that are susceptible to reasoning errors and inherently constrained in modeling the multifaceted signals underlying document relevance. To resolve this dilemma, we propose MERIT-Rank(Multi-perspective Evidence and Reasoning Integration for Text Reranking), a framework that models complementary reasoning trajectories to improve reranking robustness. MERIT-Rank formulates a Multi-Trajectory Reasoning Space (MTRS) that evaluates query-document relevance from multiple perspectives and introduces a joint reranker that consolidates these reasoning paths into a unified ranking decision. We further develop Progressive Rank Policy Optimization (PRPO), a progressive training framework that stabilizes reasoning trajectories while continually improving ranking quality through staged optimization objectives. Experiments on both reasoning-intensive and traditional retrieval benchmarks show that MERIT-Rank consistently achieves superior performance over competitive baselines. The 4B model notably outperforms most 7B and even 32B rerankers on BRIGHT.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{liu2026think,
  title = {Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking},
  author = {Lijun Liu and Zhengzong Chen and Wenyan Li and Yuanyuan Zhao and Fei Huang},
  year = {2026},
  abstract = {Reasoning-based reranking with Large Language Models (LLMs) has shown promising improvements in text ranking. However, current methods predominantly rely on a single reasoning trajectory, resulting in rankings that are susceptible to reasoning errors and inherently constrained in modeling the multifaceted signals underlying document relevance. To resolve this dilemma, we propose MERIT-Rank(Multi-perspective Evidence and Reasoning Integration for Text Reranking), a framework that models complemen},
  url = {https://arxiv.org/abs/2609.20131},
  keywords = {cs.IR, cs.CL},
  eprint = {2609.20131},
  archiveprefix = {arXiv},
}

Metadata

{}