Leveraging Large Language Models for Automated Dialogue Analysis

Sarah E. Finch, Ellie S. Paek, Jinho D. Choi


Abstract
Developing high-performing dialogue systems benefits from the automatic identification of undesirable behaviors in system responses. However, detecting such behaviors remains challenging, as it draws on a breadth of general knowledge and understanding of conversational practices. Although recent research has focused on building specialized classifiers for detecting specific dialogue behaviors, the behavior coverage is still incomplete and there is a lack of testing on real-world human-bot interactions. This paper investigates the ability of a state-of-the-art large language model (LLM), ChatGPT-3.5, to perform dialogue behavior detection for nine categories in real human-bot dialogues. We aim to assess whether ChatGPT can match specialized models and approximate human performance, thereby reducing the cost of behavior detection tasks. Our findings reveal that neither specialized models nor ChatGPT have yet achieved satisfactory results for this task, falling short of human performance. Nevertheless, ChatGPT shows promising potential and often outperforms specialized detection models. We conclude with an in-depth examination of the prevalent shortcomings of ChatGPT, offering guidance for future research to enhance LLM capabilities.
Anthology ID:
2023.sigdial-1.20
Volume:
Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2023
Address:
Prague, Czechia
Editors:
Svetlana Stoyanchev, Shafiq Joty, David Schlangen, Ondrej Dusek, Casey Kennington, Malihe Alikhani
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
202–215
Language:
URL:
https://aclanthology.org/2023.sigdial-1.20
DOI:
10.18653/v1/2023.sigdial-1.20
Bibkey:
Cite (ACL):
Sarah E. Finch, Ellie S. Paek, and Jinho D. Choi. 2023. Leveraging Large Language Models for Automated Dialogue Analysis. In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 202–215, Prague, Czechia. Association for Computational Linguistics.
Cite (Informal):
Leveraging Large Language Models for Automated Dialogue Analysis (Finch et al., SIGDIAL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.sigdial-1.20.pdf