Year: 2024
Type: preprint
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.
Source: arXiv (Cornell University)
Author: Dhole, Kaustubh D.
Institution: Emory University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4405252961