Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment

Kun Luo, Minghao Qin, Zheng Liu, Shitao Xiao, Jun Zhao, Kang Liu


Abstract
Pre-trained language models like BERT and T5 serve as crucial backbone encoders for dense retrieval. However, these models often exhibit limited generalization capabilities and face challenges in improving in-domain accuracy. Recent research has explored using large language models (LLMs) as retrievers, achieving state-of-the-art performance across various tasks. Despite these advancements, the specific benefits of LLMs over traditional retrievers and the impact of different LLM configurations—such as parameter sizes, pre-training duration, and alignment processes—on retrieval tasks remain unclear. In this work, we conduct a comprehensive empirical study on a wide range of retrieval tasks, including in-domain accuracy, data efficiency, zero-shot generalization, lengthy retrieval, instruction-based retrieval, and multi-task learning. We evaluate over 15 different backbone LLMs and non-LLMs. Our findings reveal that larger models and extensive pre-training consistently enhance in-domain accuracy and data efficiency. Additionally, larger models demonstrate significant potential in zero-shot generalization, lengthy retrieval, instruction-based retrieval, and multi-task learning. These results underscore the advantages of LLMs as versatile and effective backbone encoders in dense retrieval, providing valuable insights for future research and development in this field.
Anthology ID:
2024.emnlp-main.80
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1354–1365
Language:
URL:
https://aclanthology.org/2024.emnlp-main.80
DOI:
10.18653/v1/2024.emnlp-main.80
Bibkey:
Cite (ACL):
Kun Luo, Minghao Qin, Zheng Liu, Shitao Xiao, Jun Zhao, and Kang Liu. 2024. Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1354–1365, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment (Luo et al., EMNLP 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.emnlp-main.80.pdf