Detail

Publication date: 25 de February, 2025

Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants

Conversational systems must be robust to user interactions that naturally exhibit diverse conversational traits. Capturing and simulating these diverse traits coherently and efficiently presents a complex challenge. This talk introduces Multi-Trait Adaptive Decoding (mTAD), a method that generates diverse user profiles at decoding-time by sampling from various trait-specific Language Models (LMs). mTAD provides an adaptive and scalable approach to user simulation, enabling the creation of multiple user profiles without the need for additional fine-tuning. By analyzing real-world dialogues from the Conversational Task Assistant (CTA) domain, we identify key conversational traits and developed a framework to generate profile-aware dialogues that enhance conversational diversity. Experimental results validate the effectiveness of our approach in modeling single-traits using specialized LMs, which can capture less common patterns, even in out-of-domain tasks. Furthermore, the results demonstrate that mTAD is a robust and flexible framework for combining diverse user simulators.

Presenter

Rafael Ferreira (NOVA FCT and NOVA LINCS)

URL https://videoconf-colibri.zoom.us/j/92950889155?pwd=YXN6MFNwaDVxbGh4RHQ5d3N0VWhLUT09
Date 26/03/2025 2:00 pm
Location DI Seminars Room and Zoom
Host Bio Rafael Ferreira is a 4th-year PhD student in Computer Science at NOVA School of Science and Technology. His research focuses on AI-driven conversational agents designed to assist users with manual tasks, with a particular emphasis on user simulation and rating prediction to evaluate system robustness. Rafael was also the team leader of the TWIZ team, which achieved award-winning success in both editions of the Alexa Prize TaskBot Challenge.