Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems
Vishal Vivek Saley, Rocktim Jyoti Das, Dinesh Raghu, Mausam .
Abstract
End-to-end Task-Oriented Dialog (TOD) systems typically require extensive training datasets to perform well. In contrast, large language model (LLM) based TOD systems can excel even with limited data due to their ability to learn tasks through in-context exemplars. However, these models lack alignment with the style of responses in training data and often generate comprehensive responses, making it difficult for users to grasp the information quickly. In response, we propose SyncTOD that synergizes LLMs with task-specific hints to improve alignment in low-data settings. SyncTOD employs small auxiliary models to provide hints and select exemplars for in-context prompts. With ChatGPT, SyncTOD achieves superior performance compared to LLM-based baselines and SoTA models in low-data settings, while retaining competitive performance in full-data settings.- Anthology ID:
- 2024.emnlp-main.320
- Volume:
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5596–5612
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/2024.emnlp-main.320/
- DOI:
- 10.18653/v1/2024.emnlp-main.320
- Cite (ACL):
- Vishal Vivek Saley, Rocktim Jyoti Das, Dinesh Raghu, and Mausam .. 2024. Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 5596–5612, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems (Saley et al., EMNLP 2024)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/2024.emnlp-main.320.pdf