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

October 20, 2023 ยท Entered Twilight ยท ๐Ÿ› Conference on Empirical Methods in Natural Language Processing

๐Ÿ’ค TWILIGHT: Eternal Rest
Repo abandoned since publication

Repo contents: .gitignore, LICENSE, README.md, ds_config_s3.json, fuse.py, prompts.py, run.py

Authors Shengyao Zhuang, Bing Liu, Bevan Koopman, Guido Zuccon arXiv ID 2310.13243 Category cs.IR: Information Retrieval Cross-listed cs.CL Citations 73 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/ielab/llm-qlm โญ 17 Last Checked 1 month ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Information Retrieval