1 code implementation • 24 May 2024 • Vishal Vivek Saley, Rocktim Jyoti Das, Dinesh Raghu, Mausam
As the number of train dialogs increases, supervised SoTA models surpass in-context learning LLMs as they learn to better align with the style of the system responses in the training data, which LLMs struggle to mimic.
1 code implementation • 26 May 2023 • Vishal Vivek Saley, Rocktim Jyoti Das, Dinesh Raghu, Mausam
In this work, we define the novel problem of learning a TOD agent with dialog-KB inconsistencies in the training data.