PyTerrier-GenRank: The PyTerrier Plugin for Reranking with Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Dhole, Kaustubh D.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913600547848192
author Dhole, Kaustubh D.
author_facet Dhole, Kaustubh D.
contents Using LLMs as rerankers requires experimenting with various hyperparameters, such as prompt formats, model choice, and reformulation strategies. We introduce PyTerrier-GenRank, a PyTerrier plugin to facilitate seamless reranking experiments with LLMs, supporting popular ranking strategies like pointwise and listwise prompting. We validate our plugin through HuggingFace and OpenAI hosted endpoints.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05339
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PyTerrier-GenRank: The PyTerrier Plugin for Reranking with Large Language Models
Dhole, Kaustubh D.
Information Retrieval
Artificial Intelligence
Computation and Language
H.3.3
Using LLMs as rerankers requires experimenting with various hyperparameters, such as prompt formats, model choice, and reformulation strategies. We introduce PyTerrier-GenRank, a PyTerrier plugin to facilitate seamless reranking experiments with LLMs, supporting popular ranking strategies like pointwise and listwise prompting. We validate our plugin through HuggingFace and OpenAI hosted endpoints.
title PyTerrier-GenRank: The PyTerrier Plugin for Reranking with Large Language Models
topic Information Retrieval
Artificial Intelligence
Computation and Language
H.3.3
url https://arxiv.org/abs/2412.05339