TY - GEN
T1 - Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants
AU - Ferreira, Rafael
AU - Semedo, David
AU - Magalhães, João
N1 - info:eu-repo/grantAgreement/FCT/Concurso de avaliação no âmbito do Programa Plurianual de Financiamento de Unidades de I&D (2017%2F2018) - Financiamento Programático/UIDP%2F04516%2F2020/PT#
info:eu-repo/grantAgreement/FCT//UI%2FBD%2F151261%2F2021/PT#
Publisher Copyright:
© 2024 Association for Computational Linguistics.
PY - 2024/11
Y1 - 2024/11
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85217622398&partnerID=8YFLogxK
U2 - 10.18653/v1/2024.findings-emnlp.945
DO - 10.18653/v1/2024.findings-emnlp.945
M3 - Conference contribution
AN - SCOPUS:85217622398
T3 - EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2024
SP - 16105
EP - 16130
BT - EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2024
A2 - Al-Onaizan, Yaser
A2 - Bansal, Mohit
A2 - Chen, Yun-Nung
PB - Association for Computational Linguistics (ACL)
T2 - 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024
Y2 - 12 November 2024 through 16 November 2024
ER -