Tailored Conversations beyond LLMs: A RL-Based Dialogue Manager

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Galland, Lucie, Pelachaud, Catherine, Pecune, Florian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911044167794688
author Galland, Lucie
Pelachaud, Catherine
Pecune, Florian
author_facet Galland, Lucie
Pelachaud, Catherine
Pecune, Florian
contents In this work, we propose a novel framework that integrates large language models (LLMs) with an RL-based dialogue manager for open-ended dialogue with a specific goal. By leveraging hierarchical reinforcement learning to model the structured phases of dialogue and employ meta-learning to enhance adaptability across diverse user profiles, our approach enhances adaptability and efficiency, enabling the system to learn from limited data, transition fluidly between dialogue phases, and personalize responses to heterogeneous patient needs. We apply our framework to Motivational Interviews, aiming to foster behavior change, and demonstrate that the proposed dialogue manager outperforms a state-of-the-art LLM baseline in terms of reward, showing a potential benefit of conditioning LLMs to create open-ended dialogue systems with specific goals.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19652
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Tailored Conversations beyond LLMs: A RL-Based Dialogue Manager
Galland, Lucie
Pelachaud, Catherine
Pecune, Florian
Computation and Language
Artificial Intelligence
In this work, we propose a novel framework that integrates large language models (LLMs) with an RL-based dialogue manager for open-ended dialogue with a specific goal. By leveraging hierarchical reinforcement learning to model the structured phases of dialogue and employ meta-learning to enhance adaptability across diverse user profiles, our approach enhances adaptability and efficiency, enabling the system to learn from limited data, transition fluidly between dialogue phases, and personalize responses to heterogeneous patient needs. We apply our framework to Motivational Interviews, aiming to foster behavior change, and demonstrate that the proposed dialogue manager outperforms a state-of-the-art LLM baseline in terms of reward, showing a potential benefit of conditioning LLMs to create open-ended dialogue systems with specific goals.
title Tailored Conversations beyond LLMs: A RL-Based Dialogue Manager
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.19652