Metraipolis › archive › dc_3cd9d1f098be
Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking — arXiv:2609.20131
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20131
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:48:47.834Z
- SHA-256 of the archived text
6e0a7a91dbb54b009de1d0429227c498b2ccf35a90aa46ad4d36c7beeee9aa92- Stable URL of this page
https://metraipolis.com/documento/dc_3cd9d1f098be
How to cite
Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking — arXiv:2609.20131 — arXiv (en), https://arxiv.org/abs/2609.20131 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3cd9d1f098be (Metraipolis archive dc_3cd9d1f098be, sha256 6e0a7a91dbb54b009de1d0429227c498b2ccf35a90aa46ad4d36c7beeee9aa92)
BibTeX
@misc{dc3cd9d1f098be,
title = {Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking — arXiv:2609.20131},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20131},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3cd9d1f098be; sha256 6e0a7a91dbb54b009de1d0429227c498b2ccf35a90aa46ad4d36c7beeee9aa92},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20131. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CL). Categorie arXiv: Information Retrieval (cs.IR) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.20131 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T03:24:08.196Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).