EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wan, Chenwei, Labeau, Matthieu, Clavel, Chloé
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918197186265088
author Wan, Chenwei
Labeau, Matthieu
Clavel, Chloé
author_facet Wan, Chenwei
Labeau, Matthieu
Clavel, Chloé
contents Designing emotionally intelligent conversational systems to provide comfort and advice to people experiencing distress is a compelling area of research. Recently, with advancements in large language models (LLMs), end-to-end dialogue agents without explicit strategy prediction steps have become prevalent. However, implicit strategy planning lacks transparency, and recent studies show that LLMs' inherent preference bias towards certain socio-emotional strategies hinders the delivery of high-quality emotional support. To address this challenge, we propose decoupling strategy prediction from language generation, and introduce a novel dialogue strategy prediction framework, EmoDynamiX, which models the discourse dynamics between user fine-grained emotions and system strategies using a heterogeneous graph for better performance and transparency. Experimental results on two ESC datasets show EmoDynamiX outperforms previous state-of-the-art methods with a significant margin (better proficiency and lower preference bias). Our approach also exhibits better transparency by allowing backtracing of decision making.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08782
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics
Wan, Chenwei
Labeau, Matthieu
Clavel, Chloé
Computation and Language
Designing emotionally intelligent conversational systems to provide comfort and advice to people experiencing distress is a compelling area of research. Recently, with advancements in large language models (LLMs), end-to-end dialogue agents without explicit strategy prediction steps have become prevalent. However, implicit strategy planning lacks transparency, and recent studies show that LLMs' inherent preference bias towards certain socio-emotional strategies hinders the delivery of high-quality emotional support. To address this challenge, we propose decoupling strategy prediction from language generation, and introduce a novel dialogue strategy prediction framework, EmoDynamiX, which models the discourse dynamics between user fine-grained emotions and system strategies using a heterogeneous graph for better performance and transparency. Experimental results on two ESC datasets show EmoDynamiX outperforms previous state-of-the-art methods with a significant margin (better proficiency and lower preference bias). Our approach also exhibits better transparency by allowing backtracing of decision making.
title EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics
topic Computation and Language
url https://arxiv.org/abs/2408.08782