Enregistré dans:
Détails bibliographiques
Auteurs principaux: Podolak, Jakub, Peric, Leon, Janicijevic, Mina, Petcu, Roxana
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2504.10509
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912328596848640
author Podolak, Jakub
Peric, Leon
Janicijevic, Mina
Petcu, Roxana
author_facet Podolak, Jakub
Peric, Leon
Janicijevic, Mina
Petcu, Roxana
contents This study presents a comprehensive reproducibility and extension analysis of the Setwise prompting methodology for zero-shot ranking with Large Language Models (LLMs), as proposed by Zhuang et al. We evaluate its effectiveness and efficiency compared to traditional Pointwise, Pairwise, and Listwise approaches in document ranking tasks. Our reproduction confirms the findings of Zhuang et al., highlighting the trade-offs between computational efficiency and ranking effectiveness in Setwise methods. Building on these insights, we introduce Setwise Insertion, a novel approach that leverages the initial document ranking as prior knowledge, reducing unnecessary comparisons and uncertainty by focusing on candidates more likely to improve the ranking results. Experimental results across multiple LLM architectures (Flan-T5, Vicuna, and Llama) show that Setwise Insertion yields a 31% reduction in query time, a 23% reduction in model inferences, and a slight improvement in reranking effectiveness compared to the original Setwise method. These findings highlight the practical advantage of incorporating prior ranking knowledge into Setwise prompting for efficient and accurate zero-shot document reranking.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10509
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Reproducibility: Advancing Zero-shot LLM Reranking Efficiency with Setwise Insertion
Podolak, Jakub
Peric, Leon
Janicijevic, Mina
Petcu, Roxana
Information Retrieval
Artificial Intelligence
This study presents a comprehensive reproducibility and extension analysis of the Setwise prompting methodology for zero-shot ranking with Large Language Models (LLMs), as proposed by Zhuang et al. We evaluate its effectiveness and efficiency compared to traditional Pointwise, Pairwise, and Listwise approaches in document ranking tasks. Our reproduction confirms the findings of Zhuang et al., highlighting the trade-offs between computational efficiency and ranking effectiveness in Setwise methods. Building on these insights, we introduce Setwise Insertion, a novel approach that leverages the initial document ranking as prior knowledge, reducing unnecessary comparisons and uncertainty by focusing on candidates more likely to improve the ranking results. Experimental results across multiple LLM architectures (Flan-T5, Vicuna, and Llama) show that Setwise Insertion yields a 31% reduction in query time, a 23% reduction in model inferences, and a slight improvement in reranking effectiveness compared to the original Setwise method. These findings highlight the practical advantage of incorporating prior ranking knowledge into Setwise prompting for efficient and accurate zero-shot document reranking.
title Beyond Reproducibility: Advancing Zero-shot LLM Reranking Efficiency with Setwise Insertion
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2504.10509