DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models

Songbo Hu, Xiaobin Wang, Moy Yuan, Anna Korhonen, Ivan Vulić


Abstract
We present DIALIGHT, a toolkit for developing and evaluating multilingual Task-Oriented Dialogue (ToD) systems which facilitates systematic evaluations and comparisons between ToD systems using fine-tuning of Pretrained Language Models (PLMs) and those utilising the zero-shot and in-context learning capabilities of Large Language Models (LLMs). In addition to automatic evaluation, this toolkit features (i) a secure, user-friendly web interface for fine-grained human evaluation at both local utterance level and global dialogue level, and (ii) a microservice-based backend, improving efficiency and scalability. Our evaluations reveal that while PLM fine-tuning leads to higher accuracy and coherence, LLM-based systems excel in producing diverse and likeable responses. However, we also identify significant challenges of LLMs in adherence to task-specific instructions and generating outputs in multiple languages, highlighting areas for future research. We hope this open-sourced toolkit will serve as a valuable resource for researchers aiming to develop and properly evaluate multilingual ToD systems and will lower, currently still high, entry barriers in the field.
Anthology ID:
2024.naacl-demo.4
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kai-Wei Chang, Annie Lee, Nazneen Rajani
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
36–52
Language:
URL:
https://aclanthology.org/2024.naacl-demo.4
DOI:
10.18653/v1/2024.naacl-demo.4
Bibkey:
Cite (ACL):
Songbo Hu, Xiaobin Wang, Moy Yuan, Anna Korhonen, and Ivan Vulić. 2024. DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations), pages 36–52, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models (Hu et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-demo.4.pdf