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

Abstract

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.

Cited by in corpus (2)

• Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
• Artifact Sharing for Information Retrieval Research