TY - GEN
T1 - PTP
T2 - 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023
AU - Chen, Lichang
AU - Chen, Jiuhai
AU - Huang, Heng
AU - Cheng, Minhao
N1 - Publisher Copyright:
©2023 Association for Computational Linguistics.
PY - 2023
Y1 - 2023
N2 - Recent studies show that prompt tuning can better leverage the power of large language models than fine-tuning on downstream natural language understanding tasks. Nonetheless, current prompt tuning methods encounter instability during training, marked by a high variance in scores given different random seeds. In addressing this crucial issue, we uncover that the loss landscape of standard prompt tuning, when visualized, is remarkably steep, i.e., minor alterations in the input data can trigger substantial fluctuations in the loss landscape, which is an essential factor that leads to the training instability. In light of this finding, we incorporate perturbation-based regularizers to temper the loss landscape within the prompt tuning process. We thus present a novel algorithm, called Prompt Tuning with Perturbation-based regularizer (PTP), that can significantly reduce training instability and concurrently enhance the performance of prompt tuning. Specifically, we design two variants of perturbation-based regularizers: one that employs random noise, and another that uses an adversarial approach. Importantly, our proposed perturbations display flexibility in both the text and embedding spaces. Extensive experiments show the effectiveness of our proposed methods in stabilizing the training. Our new algorithms improve the state-of-the-art prompt tuning methods by 1.94% and 2.34% on SuperGLUE and FewGLUE benchmarks, respectively.
AB - Recent studies show that prompt tuning can better leverage the power of large language models than fine-tuning on downstream natural language understanding tasks. Nonetheless, current prompt tuning methods encounter instability during training, marked by a high variance in scores given different random seeds. In addressing this crucial issue, we uncover that the loss landscape of standard prompt tuning, when visualized, is remarkably steep, i.e., minor alterations in the input data can trigger substantial fluctuations in the loss landscape, which is an essential factor that leads to the training instability. In light of this finding, we incorporate perturbation-based regularizers to temper the loss landscape within the prompt tuning process. We thus present a novel algorithm, called Prompt Tuning with Perturbation-based regularizer (PTP), that can significantly reduce training instability and concurrently enhance the performance of prompt tuning. Specifically, we design two variants of perturbation-based regularizers: one that employs random noise, and another that uses an adversarial approach. Importantly, our proposed perturbations display flexibility in both the text and embedding spaces. Extensive experiments show the effectiveness of our proposed methods in stabilizing the training. Our new algorithms improve the state-of-the-art prompt tuning methods by 1.94% and 2.34% on SuperGLUE and FewGLUE benchmarks, respectively.
UR - http://www.scopus.com/inward/record.url?scp=85184808328&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85184808328&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85184808328
T3 - EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 13512
EP - 13525
BT - EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings
A2 - Bouamor, Houda
A2 - Pino, Juan
A2 - Bali, Kalika
PB - Association for Computational Linguistics (ACL)
Y2 - 6 December 2023 through 10 December 2023
ER -