Ferreira, RafaelSemedo, DavidMagalhães, João2025-03-272025-03-272024-119798891761681PURE: 113362679PURE UUID: 05c6ba34-e915-40f7-8c4a-cf1be82ab9c2Scopus: 85217622398ORCID: /0000-0002-2403-0058/work/181053523http://hdl.handle.net/10362/181567Publisher Copyright: © 2024 Association for Computational Linguistics.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.261762025engComputational Theory and MathematicsComputer Science ApplicationsInformation SystemsLinguistics and Languageconference object10.18653/v1/2024.findings-emnlp.945https://www.scopus.com/pages/publications/85217622398