[go: up one dir, main page]

Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking

Shengyao Zhuang, Bing Liu, Bevan Koopman, Guido Zuccon


Abstract
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.
Anthology ID:
2023.findings-emnlp.590
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8807–8817
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.590
DOI:
10.18653/v1/2023.findings-emnlp.590
Bibkey:
Cite (ACL):
Shengyao Zhuang, Bing Liu, Bevan Koopman, and Guido Zuccon. 2023. Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8807–8817, Singapore. Association for Computational Linguistics.
Cite (Informal):
Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking (Zhuang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.590.pdf