Signals 4 · free daily AI digest

Re$^3$Rank: Listwise Reranking with Reasoning-Conditioned Retrieval Heads

Paper recorded by Signals 4 on 2026-11-02 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-11-02 on arXiv · recorded by Signals 4 on 2026-11-03

Category: cs.CL · 自然语言处理 · first seen 2026-11-03

Abstract

Attention-based rerankers score each candidate by the attention mass that retrieval heads route to it from the question, but the question, serving as a fixed query, carries limited information for locating relevant evidence. We propose Re$^3$Rank, a listwise reranker built on reasoning-conditioned retrieval heads (RRHeads). A generator first writes a reasoning trace over the question and the candi

Read on arXiv →

#26 most recent of 628 cs.CL papers we have recorded · ↑ newer: SMILE: A Structured Multi-Agent Clinical Reasoning for Liver Ultrasoun · ↓ older: FindLink: Learning to Assess Scientific Connections from Source-Ground
Cite this page: Re$^3$Rank: Listwise Reranking with Reasoning-Conditioned Retrieval Heads: the #26 most recent of 628 cs.CL papers we have recorded (as of 2026-11-02). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/re-3-rank-listwise-reranking-with-reasoning-conditioned-retrieval-heads.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions