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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ferreira, Rafael, Semedo, David, Magalhães, João
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929562019954688
author Ferreira, Rafael
Semedo, David
Magalhães, João
author_facet Ferreira, Rafael
Semedo, David
Magalhães, João
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12891
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants
Ferreira, Rafael
Semedo, David
Magalhães, João
Computation and Language
Artificial Intelligence
Human-Computer Interaction
I.2.7
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.
title Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
I.2.7
url https://arxiv.org/abs/2410.12891