You're currently viewing an old version of this dataset. To see the current version, click here.

Leveraging Explicit Procedural Instructions for Data-Efficient Action Prediction

Task-oriented dialogue systems often require agents to enact complex, multi-step procedures in order to meet user requests. The proposed Knowledge-Augmented Dialogue System (KADS) combines a large language model with a knowledge retrieval module that pulls documents outlining relevant procedures from a predefined set of policies, given a user-agent interaction.

Data and Resources

This dataset has no data

Cite this as

Julia White, Arushi Raghuvanshi, Yada Pruksachatkun (2024). Dataset: Leveraging Explicit Procedural Instructions for Data-Efficient Action Prediction. https://doi.org/10.57702/akgfirea

Private DOI This DOI is not yet resolvable.
It is available for use in manuscripts, and will be published when the Dataset is made public.

Additional Info

Field	Value
Created	December 16, 2024
Last update	December 16, 2024
Defined In	https://doi.org/10.48550/arXiv.2306.03959
Author	Julia White
More Authors	Arushi Raghuvanshi Yada Pruksachatkun