Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants
This work addresses the problem of improving conversational diversity for task assistants, but it appears incremental as it builds on existing methods for user simulation.
The paper tackles the challenge of simulating diverse conversational traits in user interactions for conversational systems by introducing Multi-Trait Adaptive Decoding (mTAD), which generates multiple user profiles at decoding-time without fine-tuning, and experimental results validate its effectiveness in modeling traits and enhancing diversity.
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 paper 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.