5 papers
TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons
Emre Can Acikgoz, Carl Guo, Suvodip Dey +4
Task-oriented dialogue (TOD) systems are experiencing a revolution driven by Large Language Models (LLMs), yet the evaluation methodologies for these systems remain insufficient fo…
Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling
Suvodip Dey, Yi-Jyun Sun, Gokhan Tur +1
Recent LLMs have enabled significant advancements for conversational agents. However, they are also well known to hallucinate, producing responses that seem plausible but are factu…
ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents
Vardhan Dongre, Xiaocheng Yang, Emre Can Acikgoz +3
Large language model (LLM)-based agents are increasingly employed to interact with external environments (e.g., games, APIs, world models) to solve user-provided tasks. However, cu…
Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems
Mert Ä°nan, Anthony Sicilia, Suvodip Dey +6
While theories of discourse and cognitive science have long recognized the value of unhurried pacing, recent dialogue research tends to minimize friction in conversational systems.…
BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation
Suvodip Dey, Maunendra Sankar Desarkar
The standard language modeling (LM) loss by itself has been shown to be inadequate for effective dialogue modeling. As a result, various training approaches, such as auxiliary loss…