Research Projects

A Taxonomy for Positive Friction

Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems

Read more »

Accountability Modeling

Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling

Read more »

Sycophancy in Language Model

Accounting for Sycophancy in Language Model Uncertainty Estimation

Read more »

ReSpAct Harmonizing Reasoning, Speaking, and Acting

ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents

Read more »