# Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers

arXiv: https://arxiv.org/abs/2410.02642 · HTML: https://mlsanity.com/paper/2410.02642/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 36 of its 50 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 30 of 36)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Distilling Knowledge from Reader to Retriever for Question Answering](https://mlsanity.com/paper/2012.04584/) (2020)
- [Multi-Stage Document Ranking with BERT](https://mlsanity.com/paper/1910.14424/) (2019)
- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)
- [Improving Passage Retrieval with Zero-Shot Question Generation](https://mlsanity.com/paper/2204.07496/) (2022)
- [RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!](https://mlsanity.com/paper/2312.02724/) (2023)
- [Attention Sorting Combats Recency Bias In Long Context Language Models](https://mlsanity.com/paper/2310.01427/) (2023)
- [Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels](https://mlsanity.com/paper/2310.14122/) (2023)
- [Zero-Shot Listwise Document Reranking with a Large Language Model](https://mlsanity.com/paper/2305.02156/) (2023)

## Built on by (most cited first, 30 of 43)

- [Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning](https://mlsanity.com/paper/2503.06034/) (2025)
- [Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking](https://mlsanity.com/paper/2506.09944/) (2025)
- [DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.07233/) (2025)
- [Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.02464/) (2025)
- [LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Reranking](https://mlsanity.com/paper/2504.07439/) (2025)
- [DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation](https://mlsanity.com/paper/2508.16998/) (2025)
- [Scalable In-context Ranking with Generative Models](https://mlsanity.com/paper/2510.05396/) (2025)
- [How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective](https://mlsanity.com/paper/2504.07898/) (2025)
- [LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation](https://mlsanity.com/paper/2601.05192/) (2026)
- [RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback](https://mlsanity.com/paper/2508.05512/) (2025)
- [Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization](https://mlsanity.com/paper/2601.12078/) (2026)
- [ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting](https://mlsanity.com/paper/2602.19969/) (2026)
- [Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance](https://mlsanity.com/paper/2503.23239/) (2025)
- [How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models](https://mlsanity.com/paper/2508.16757/) (2025)
- [Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation](https://mlsanity.com/paper/2508.18142/) (2025)
- [E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search](https://mlsanity.com/paper/2510.22733/) (2025)
- [Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration](https://mlsanity.com/paper/2604.10150/) (2026)
- [Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers](https://mlsanity.com/paper/2507.06223/) (2025)
- [Looking Is Not Picking: An Attention-Segment Account of Tool-Selection Failures in LLM Agents](https://mlsanity.com/paper/2606.16364/) (2026)
- [HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads](https://mlsanity.com/paper/2604.17237/) (2026)
- [Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization](https://mlsanity.com/paper/2604.22345/) (2026)
- [Hint-Augmented Re-ranking: Efficient Product Search using LLM-Based Query Decomposition](https://mlsanity.com/paper/2511.13994/) (2025)
- [An Efficient Long-Context Ranking Architecture With Calibrated LLM Distillation: Application to Person-Job Fit](https://mlsanity.com/paper/2601.10321/) (2026)
- [Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning](https://mlsanity.com/paper/2604.02091/) (2026)
- [Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models](https://mlsanity.com/paper/2605.27243/) (2026)
- [Lost at the End: Primacy Bias in Multimodal Retrieval-Augmented Question Answering](https://mlsanity.com/paper/2606.16494/) (2026)
- [Rationale-Augmented Retrieval with Constrained LLM Re-Ranking for Task Discovery](https://mlsanity.com/paper/2510.05131/) (2025)
- [Embedding-Based Context-Aware Reranker](https://mlsanity.com/paper/2510.13329/) (2025)
- [Citation Failure: Definition, Analysis and Efficient Mitigation](https://mlsanity.com/paper/2510.20303/) (2025)
- [Zero-shot Vision-Language Reranking for Cross-View Geolocalization](https://mlsanity.com/paper/2603.27251/) (2026)

## Abstract (arXiv)

Information retrieval (IR) systems have played a vital role in modern digital life and have cemented their continued usefulness in this new era of generative AI via retrieval-augmented generation. With strong language processing capabilities and remarkable versatility, large language models (LLMs) have become popular choices for zero-shot re-ranking in IR systems. So far, LLM-based re-ranking methods rely on strong generative capabilities, which restricts their use to either specialized or powerful proprietary models. Given these restrictions, we ask: is autoregressive generation necessary and optimal for LLMs to perform re-ranking? We hypothesize that there are abundant signals relevant to re-ranking within LLMs that might not be used to their full potential via generation. To more directly leverage such signals, we propose in-context re-ranking (ICR), a novel method that leverages the change in attention pattern caused by the search query for accurate and efficient re-ranking. To mitigate the intrinsic biases in LLMs, we propose a calibration method using a content-free query. Due to the absence of generation, ICR only requires two (O(1)) forward passes to re-rank N documents, making it substantially more efficient than generative re-ranking methods that require at least O(N) forward passes. Our novel design also enables ICR to be applied to any LLM without specialized training while guaranteeing a well-formed ranking. Extensive experiments with two popular open-weight LLMs on standard single-hop and multi-hop information retrieval benchmarks show that ICR outperforms RankGPT while cutting the latency by more than 60% in practice. Through detailed analyses, we show that ICR's performance is specially strong on tasks that require more complex re-ranking signals. Our findings call for further exploration on novel ways of utilizing open-weight LLMs beyond text generation.