Abstract
Pre-trained large language models, such as ChatGPT, archive outstanding performance in various reasoning tasks without supervised training and were found to have outperformed crowdsourcing workers. Nonetheless, ChatGPT’s performance in the task of implicit discourse relation classification, prompted by a standard multiple-choice question, is still far from satisfactory and considerably inferior to state-of-the-art supervised approaches. This work investigates several proven prompting techniques to improve ChatGPT’s recognition of discourse relations. In particular, we experimented with breaking down the classification task that involves numerous abstract labels into smaller subtasks. Nonetheless, experiment results show that the inference accuracy hardly changes even with sophisticated prompt engineering, suggesting that implicit discourse relation classification is not yet resolvable under zero-shot or few-shot settings.
Original language | English |
---|---|
Title of host publication | Proceedings of The 18th Linguistic Annotation Workshop (LAW-XVIII) |
Editors | Sophie Henning, Manfred Stede |
Publisher | Association for Computational Linguistics |
Pages | 150-165 |
Number of pages | 16 |
ISBN (Electronic) | 9798891760738 |
Publication status | Published - 2024 |
Event | 18th Linguistic Annotation Workshop, LAW 2024 - St. Julian's, Malta Duration: 22 Mar 2024 → … |
Conference
Conference | 18th Linguistic Annotation Workshop, LAW 2024 |
---|---|
Country/Territory | Malta |
City | St. Julian's |
Period | 22/03/24 → … |
Bibliographical note
Publisher Copyright:© 2024 Association for Computational Linguistics.