Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers

Weng Tam, Xiao Liu, Kaixuan Ji, Lilong Xue, Jiahua Liu, Tao Li, Yuxiao Dong, Jie Tang

Abstract
Prompt tuning attempts to update few task-specific parameters in pre-trained models. It has achieved comparable performance to fine-tuning of the full parameter set on both language understanding and generation tasks. In this work, we study the problem of prompt tuning for neural text retrievers. We introduce parameter-efficient prompt tuning for text retrieval across in-domain, cross-domain, and cross-topic settings. Through an extensive analysis, we show that the strategy can mitigate the two issues—parameter-inefficiency and weak generalizability—faced by fine-tuning based retrieval methods. Notably, it can significantly improve the out-of-domain zero-shot generalization of the retrieval models. By updating only 0.1% of the model parameters, the prompt tuning strategy can help retrieval models achieve better generalization performance than traditional methods in which all parameters are updated. Finally, to facilitate research on retrievers’ cross-topic generalizability, we curate and release an academic retrieval dataset with 18K query-results pairs in 87 topics, making it the largest topic-specific one to date.
Anthology ID:
2023.findings-emnlp.874
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:
13117–13130
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.874
DOI:
10.18653/v1/2023.findings-emnlp.874
Bibkey:
Cite (ACL):
Weng Tam, Xiao Liu, Kaixuan Ji, Lilong Xue, Jiahua Liu, Tao Li, Yuxiao Dong, and Jie Tang. 2023. Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13117–13130, Singapore. Association for Computational Linguistics.
Cite (Informal):
Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers (Tam et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2023.findings-emnlp.874.pdf
PDF Search