Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking
This work addresses document ranking in information retrieval, offering a novel zero-shot approach that could reduce reliance on fine-tuning for practitioners.
The paper investigates the zero-shot ranking effectiveness of open-source large language models (LLMs) as Query Likelihood Models for document ranking, finding they perform robustly without instruction fine-tuning and introducing a hybrid system that achieves state-of-the-art results in zero-shot and few-shot scenarios.
In the field of information retrieval, Query Likelihood Models (QLMs) rank documents based on the probability of generating the query given the content of a document. Recently, advanced large language models (LLMs) have emerged as effective QLMs, showcasing promising ranking capabilities. This paper focuses on investigating the genuine zero-shot ranking effectiveness of recent LLMs, which are solely pre-trained on unstructured text data without supervised instruction fine-tuning. Our findings reveal the robust zero-shot ranking ability of such LLMs, highlighting that additional instruction fine-tuning may hinder effectiveness unless a question generation task is present in the fine-tuning dataset. Furthermore, we introduce a novel state-of-the-art ranking system that integrates LLM-based QLMs with a hybrid zero-shot retriever, demonstrating exceptional effectiveness in both zero-shot and few-shot scenarios. We make our codebase publicly available at https://github.com/ielab/llm-qlm.