English

Top-Down Partitioning for Efficient List-Wise Ranking

Information Retrieval 2024-05-24 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2405.14589,
  title  = {Top-Down Partitioning for Efficient List-Wise Ranking},
  author = {Andrew Parry and Sean MacAvaney and Debasis Ganguly},
  journal= {arXiv preprint arXiv:2405.14589},
  year   = {2024}
}

Comments

16 pages, 3 figures, 2 tables

R2 v1 2026-06-28T16:37:19.042Z