# Sparse Pairwise Re-ranking with Pre-trained Transformers

arXiv: https://arxiv.org/abs/2207.04470 · HTML: https://mlsanity.com/paper/2207.04470/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2022.

## Built on by (most cited first, 8 of 8)

- [A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models](https://mlsanity.com/paper/2310.09497/) (2023)
- [Ranked List Truncation for Large Language Model-based Re-Ranking](https://mlsanity.com/paper/2404.18185/) (2024)
- [LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking](https://mlsanity.com/paper/2406.00231/) (2024)
- [LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback](https://mlsanity.com/paper/2406.03363/) (2024)
- [Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers](https://mlsanity.com/paper/2507.06223/) (2025)
- [Ranking Entities along Conceptual Space Dimensions with LLMs: An Analysis of Fine-Tuning Strategies](https://mlsanity.com/paper/2402.15337/) (2024)
- [MemRerank: Preference Memory for Personalized Product Reranking](https://mlsanity.com/paper/2603.29247/) (2026)
- [Efficient Pointwise-Pairwise Learning-to-Rank for News Recommendation](https://mlsanity.com/paper/2409.17711/) (2024)

## Abstract (arXiv)

Pairwise re-ranking models predict which of two documents is more relevant to a query and then aggregate a final ranking from such preferences. This is often more effective than pointwise re-ranking models that directly predict a relevance value for each document. However, the high inference overhead of pairwise models limits their practical application: usually, for a set of k documents to be re-ranked, preferences for all k2-k comparison pairs excluding self-comparisons are aggregated. We investigate whether the efficiency of pairwise re-ranking can be improved by sampling from all pairs. In an exploratory study, we evaluate three sampling methods and five preference aggregation methods. The best combination allows for an order of magnitude fewer comparisons at an acceptable loss of retrieval effectiveness, while competitive effectiveness is already achieved with about one third of the comparisons.