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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Downloads (Pure)

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.

Original languageEnglish
Title of host publicationEMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2024
EditorsYaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
PublisherAssociation for Computational Linguistics (ACL)
Pages16105-16130
Number of pages26
ISBN (Electronic)9798891761681
DOIs
Publication statusPublished - Nov 2024
Event2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024 - Hybrid, Miami, United States
Duration: 12 Nov 202416 Nov 2024

Publication series

NameEMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2024

Conference

Conference2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024
Country/TerritoryUnited States
CityHybrid, Miami
Period12/11/2416/11/24

Cite this