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

Rafael Ferreira, David Semedo, Joao Magalhaes

Abstract
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.
Anthology ID:
2024.findings-emnlp.945
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16105–16130
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.945
DOI:
10.18653/v1/2024.findings-emnlp.945
Bibkey:
Cite (ACL):
Rafael Ferreira, David Semedo, and Joao Magalhaes. 2024. Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16105–16130, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants (Ferreira et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-emnlp.945.pdf
PDF Search