# Retrieval for Extremely Long Queries and Documents with RPRS: a Highly Efficient and Effective Transformer-based Re-Ranker

arXiv: https://arxiv.org/abs/2303.01200 · HTML: https://mlsanity.com/paper/2303.01200/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2023.

## Built on by (most cited first, 4 of 4)

- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [QBD-RankedDataGen: Generating Custom Ranked Datasets for Improving Query-By-Document Search Using LLM-Reranking with Reduced Human Effort](https://mlsanity.com/paper/2505.04732/) (2025)
- [Supporting software engineering tasks with agentic AI: Demonstration on document retrieval and test scenario generation](https://mlsanity.com/paper/2602.04726/) (2026)
- [CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering](https://mlsanity.com/paper/2609.15830/) (2026)

## Abstract (arXiv)

Retrieval with extremely long queries and documents is a well-known and challenging task in information retrieval and is commonly known as Query-by-Document (QBD) retrieval. Specifically designed Transformer models that can handle long input sequences have not shown high effectiveness in QBD tasks in previous work. We propose a Re-Ranker based on the novel Proportional Relevance Score (RPRS) to compute the relevance score between a query and the top-k candidate documents. Our extensive evaluation shows RPRS obtains significantly better results than the state-of-the-art models on five different datasets. Furthermore, RPRS is highly efficient since all documents can be pre-processed, embedded, and indexed before query time which gives our re-ranker the advantage of having a complexity of O(N) where N is the total number of sentences in the query and candidate documents. Furthermore, our method solves the problem of the low-resource training in QBD retrieval tasks as it does not need large amounts of training data, and has only three parameters with a limited range that can be optimized with a grid search even if a small amount of labeled data is available. Our detailed analysis shows that RPRS benefits from covering the full length of candidate documents and queries.