Prompt Perturbation Consistency Learning for Robust Language Models

Yao Qiang, Subhrangshu Nandi, Ninareh Mehrabi, Greg Ver Steeg, Anoop Kumar, Anna Rumshisky, Aram Galstyan


Abstract
Large language models (LLMs) have demonstrated impressive performance on a number of natural language processing tasks, such as question answering and text summarization. However, their performance on sequence labeling tasks such as intent classification and slot filling (IC-SF), which is a central component in personal assistant systems, lags significantly behind discriminative models. Furthermore, there is a lack of substantive research on robustness of LLMs to various perturbations in the input prompts. The contributions of this paper are three-fold. First, we show that fine-tuning sufficiently large LLMs can produce IC-SF performance comparable to discriminative models. Next, we systematically analyze the performance deterioration of those fine-tuned models due to three distinct yet relevant types of input perturbations - oronyms, synonyms, and paraphrasing. Finally, we propose an efficient mitigation approach, Prompt Perturbation Consistency Learning (PPCL), which works by regularizing the divergence between losses from clean and perturbed samples. Our experiments show that PPCL can recover on an average 59% and 69% of the performance drop for IC and SF tasks, respectively. Furthermore, PPCL beats data augmentation approach while using ten times fewer augmented data samples.
Anthology ID:
2024.findings-eacl.91
Volume:
Findings of the Association for Computational Linguistics: EACL 2024
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1357–1370
Language:
URL:
https://aclanthology.org/2024.findings-eacl.91
DOI:
Bibkey:
Cite (ACL):
Yao Qiang, Subhrangshu Nandi, Ninareh Mehrabi, Greg Ver Steeg, Anoop Kumar, Anna Rumshisky, and Aram Galstyan. 2024. Prompt Perturbation Consistency Learning for Robust Language Models. In Findings of the Association for Computational Linguistics: EACL 2024, pages 1357–1370, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Prompt Perturbation Consistency Learning for Robust Language Models (Qiang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-eacl.91.pdf
Video:
 https://aclanthology.org/2024.findings-eacl.91.mp4