# Top-Down Partitioning for Efficient List-Wise Ranking

arXiv: https://arxiv.org/abs/2405.14589 · HTML: https://mlsanity.com/paper/2405.14589/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2024.

## Built on by (most cited first, 13 of 13)

- [A Survey of Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08748/) (2025)
- [Guiding Retrieval using LLM-based Listwise Rankers](https://mlsanity.com/paper/2501.09186/) (2025)
- [Drowning in Documents: Consequences of Scaling Reranker Inference](https://mlsanity.com/paper/2411.11767/) (2024)
- [AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking](https://mlsanity.com/paper/2505.18512/) (2025)
- [Self-Calibrated Listwise Reranking with Large Language Models](https://mlsanity.com/paper/2411.04602/) (2024)
- [Precise Zero-Shot Pointwise Ranking with LLMs through Post-Aggregated Global Context Information](https://mlsanity.com/paper/2506.10859/) (2025)
- [Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking](https://mlsanity.com/paper/2601.18146/) (2026)
- [Likert or Not: LLM Absolute Relevance Judgments on Fine-Grained Ordinal Scales](https://mlsanity.com/paper/2505.19334/) (2025)
- [Reinforcement Speculative Decoding for Fast Ranking](https://mlsanity.com/paper/2505.20316/) (2025)
- [PyTerrier-GenRank: The PyTerrier Plugin for Reranking with Large Language Models](https://mlsanity.com/paper/2412.05339/) (2024)
- [Optimizing Compound Retrieval Systems](https://mlsanity.com/paper/2504.12063/) (2025)
- [JointRank: Rank Large Set with Single Pass](https://mlsanity.com/paper/2506.22262/) (2025)
- [Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers](https://mlsanity.com/paper/2608.26762/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have significantly impacted many facets of natural language processing and information retrieval. Unlike previous encoder-based approaches, the enlarged context window of these generative models allows for ranking multiple documents at once, commonly called list-wise ranking. However, there are still limits to the number of documents that can be ranked in a single inference of the model, leading to the broad adoption of a sliding window approach to identify the k most relevant items in a ranked list. We argue that the sliding window approach is not well-suited for list-wise re-ranking because it (1) cannot be parallelized in its current form, (2) leads to redundant computational steps repeatedly re-scoring the best set of documents as it works its way up the initial ranking, and (3) prioritizes the lowest-ranked documents for scoring rather than the highest-ranked documents by taking a bottom-up approach. Motivated by these shortcomings and an initial study that shows list-wise rankers are biased towards relevant documents at the start of their context window, we propose a novel algorithm that partitions a ranking to depth k and processes documents top-down. Unlike sliding window approaches, our algorithm is inherently parallelizable due to the use of a pivot element, which can be compared to documents down to an arbitrary depth concurrently. In doing so, we reduce the number of expected inference calls by around 33% when ranking at depth 100 while matching the performance of prior approaches across multiple strong re-rankers.