让大模型重排更简单，一键试遍提示格式与模型组合

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

• 基于PyTerrier构建插件，支持点式与列表式提示重排
• 兼容HuggingFace与OpenAI接口，可灵活切换模型与提示策略
• 适合想快速实验大模型重排效果的研究者与工程师

使用大语言模型作为重排器需要尝试多种超参数，如提示格式、模型选择和重述策略。我们提出PyTerrier-GenRank，一个PyTerrier插件，用于无缝开展大语言模型重排实验，支持常见的排序策略，如点式和列表式提示。通过HuggingFace和OpenAI托管端点验证了该插件的有效性。

原文摘要 · Abstract (English)

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.

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。