2024 · 39 citations · 10 references
ComputingComputer ScienceComputational LinguisticsInformation RetrievalNatural Language ProcessingEvaluation Of Retrieval SystemsLanguage ModelingRanking ProblemsComparative EvaluationEvaluation Of Ranking ModelsLarge Language ModelsListwise RankingPairwise Ranking ModelsPointwise RankingRanking ModelsZero-shot Language Modeling
We propose a novel zero-shot document ranking approach based on Large Language Models (LLMs): the Setwise prompting approach.Our approach complements existing prompting approaches for LLM-based zero-shot ranking: Pointwise, Pairwise, and Listwise.Through the first-of-its-kind comparative evaluation within a consistent experimental framework and considering factors like model size, token consumption, latency, among others, we show that existing approaches are inherently characterised by trade-offs between effectiveness and efficiency.We find that while Pointwise approaches score high on efficiency, they suffer from poor effectiveness.Conversely, Pairwise approaches demonstrate superior effectiveness but incur high computational overhead.Our Setwise approach, instead, reduces the number of LLM inferences and the amount of prompt token consumption during the ranking procedure, compared to previous methods.This significantly improves the efficiency of LLM-based zero-shot ranking, while also retaining high zero-shot ranking effectiveness.We make our code and results publicly available at https://github.com/ielab/llm-rankers.
10
The Art of Computer Programming
G.E. Whitesides · Nuclear Science and Engineering · 1970 · 6.1K citations
A Language Modeling Approach to Information Retrieval
Jay Ponte, W. Bruce Croft · ACM SIGIR Forum · 2017 · 2.5K citations · Full text
Document Ranking with a Pretrained Sequence-to-Sequence Model
Rodrigo Nogueira, Zhiying Jiang, Ronak Pradeep et al. · 2020 · 414 citations · Full text
Can ChatGPT Write a Good Boolean Query for Systematic Review Literature Search?
Shuai Wang, Harrisen Scells, Bevan Koopman et al. · 2023 · 202 citations