Empathic Grounding: Explorations using Multimodal Interaction and Large Language Models with Conversational Agents

TL;DR

This paper introduces 'empathic grounding' for conversational agents, emphasizing multimodal and affective communication to enhance empathy, understanding, and trust in human-agent interactions, demonstrated through a humanoid robot testbed.

Contribution

It proposes a multimodal model for empathic grounding using large language models and develops a testbed to evaluate its effectiveness in improving perceived empathy.

Findings

Empathic grounding increases perceived empathy and trust.

Multimodal affective cues improve communication quality.

Users rate robots with empathic grounding higher on emotional intelligence.

Abstract

We introduce the concept of "empathic grounding" in conversational agents as an extension of Clark's conceptualization of grounding in conversation in which the grounding criterion includes listener empathy for the speaker's affective state. Empathic grounding is generally required whenever the speaker's emotions are foregrounded and can make the grounding process more efficient and reliable by communicating both propositional and affective understanding. Both speaker expressions of affect and listener empathic grounding can be multimodal, including facial expressions and other nonverbal displays. Thus, models of empathic grounding for embodied agents should be multimodal to facilitate natural and efficient communication. We describe a multimodal model that takes as input user speech and facial expression to generate multimodal grounding moves for a listening agent using a large language model. We also describe a testbed to evaluate approaches to empathic grounding, in which a humanoid robot interviews a user about a past episode of pain and then has the user rate their perception of the robot's empathy. We compare our proposed model to one that only generates non-affective grounding cues in a between-subjects experiment. Findings demonstrate that empathic grounding increases user perceptions of empathy, understanding, emotional intelligence, and trust. Our work highlights the role of emotion awareness and multimodality in generating appropriate grounding moves for conversational agents.