Nguyen Quang Chieu
2025
Spec-TOD: A Specialized Instruction-Tuned LLM Framework for Efficient Task-Oriented Dialogue Systems
Vinh Quang Nguyen
|
Nguyen Quang Chieu
|
Hoang Viet Pham
|
Khac-Hoai Nam Bui
Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Task-oriented dialogue (TOD) systems facilitate goal-driven interactions between users and machines. While recent advances in deep learning have improved the performance, TOD systems often struggle in low-resource scenarios with limited labeled data. To address this challenge, we propose Spec-TOD, a novel framework designed to train an end-to-end TOD system with limited data. Spec-TOD introduces two main innovations: (i) a novel specialized end-to-end TOD framework that incorporates explicit task instructions for instruction-tuned large language models (LLMs), and (ii) an efficient training strategy that leverages lightweight, specialized LLMs to achieve strong performance with minimal supervision. Experiments on the MultiWOZ dataset, a widely used TOD benchmark, demonstrate that Spec-TOD achieves competitive results while significantly reducing the need for labeled data. These findings highlight the potential of the proposed framework in advancing efficient and effective TOD systems in low-resource settings.
2024
SynTOD: Augmented Response Synthesis for Robust End-to-End Task-Oriented Dialogue System
Nguyen Quang Chieu
|
Quang-Minh Tran
|
Khac-Hoai Nam Bui
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Task-oriented dialogue (TOD) systems are introduced to solve specific tasks, which focus on training multiple tasks such as language understanding, tracking states, and generating appropriate responses to help users achieve their specific goals. Currently, one of the remaining challenges in this emergent research field is the capability to produce more robust architectures fine-tuned for end-to-end TOD systems. In this study, we consider this issue by exploiting the ability of pre-trained models to provide synthesis responses, which are then used as the input for the fine-tuned process. The main idea is to overcome the gap between the training process and inference process during fine-tuning end-to-end TOD systems. The experiment on Multiwoz datasets shows the effectiveness of our model compared with strong baselines in this research field. The source code is available for further exploitation.