To Clarify or not to Clarify: A Comparative Analysis of Clarification Classification with Fine-Tuning, Prompt Tuning, and Prompt Engineering

Alina Leippert, Tatiana Anikina, Bernd Kiefer, Josef Genabith


Abstract
Misunderstandings occur all the time in human conversation but deciding on when to ask for clarification is a challenging task for conversational systems that requires a balance between asking too many unnecessary questions and running the risk of providing incorrect information. This work investigates clarification identification based on the task and data from (Xu et al., 2019), reproducing their Transformer baseline and extending it by comparing pre-trained language model fine-tuning, prompt tuning and manual prompt engineering on the task of clarification identification. Our experiments show strong performance with LM and a prompt tuning approach with BERT and RoBERTa, outperforming standard LM fine-tuning, while manual prompt engineering with GPT-3.5 proved to be less effective, although informative prompt instructions have the potential of steering the model towards generating more accurate explanations for why clarification is needed.
Anthology ID:
2024.naacl-srw.12
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Yang (Trista) Cao, Isabel Papadimitriou, Anaelia Ovalle, Marcos Zampieri, Francis Ferraro, Swabha Swayamdipta
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
105–115
Language:
URL:
https://aclanthology.org/2024.naacl-srw.12
DOI:
10.18653/v1/2024.naacl-srw.12
Bibkey:
Cite (ACL):
Alina Leippert, Tatiana Anikina, Bernd Kiefer, and Josef Genabith. 2024. To Clarify or not to Clarify: A Comparative Analysis of Clarification Classification with Fine-Tuning, Prompt Tuning, and Prompt Engineering. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 105–115, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
To Clarify or not to Clarify: A Comparative Analysis of Clarification Classification with Fine-Tuning, Prompt Tuning, and Prompt Engineering (Leippert et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-srw.12.pdf