Saved in:
Bibliographic Details
Main Authors: Müller, Ana, Jeschke, Sabina, Richert, Anja
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.10462
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913890102673408
author Müller, Ana
Jeschke, Sabina
Richert, Anja
author_facet Müller, Ana
Jeschke, Sabina
Richert, Anja
contents This paper investigates the impact of a group-adaptive conversation design in two socially interactive agents (SIAs) through two real-world studies. Both SIAs - Furhat, a social robot, and MetaHuman, a virtual agent - were equipped with a conversational artificial intelligence (CAI) backend combining hybrid retrieval and generative models. The studies were carried out in an in-the-wild setting with a total of $N = 188$ participants who interacted with the SIAs - in dyads, triads or larger groups - at a German museum. Although the results did not reveal a significant effect of the group-sensitive conversation design on perceived satisfaction, the findings provide valuable insights into the challenges of adapting CAI for multi-party interactions and across different embodiments (robot vs.\ virtual agent), highlighting the need for multimodal strategies beyond linguistic pluralization. These insights contribute to the fields of Human-Agent Interaction (HAI), Human-Robot Interaction (HRI), and broader Human-Machine Interaction (HMI), providing insights for future research on effective dialogue adaptation in group settings.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10462
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Are We Generalizing from the Exception? An In-the-Wild Study on Group-Sensitive Conversation Design in Human-Agent Interactions
Müller, Ana
Jeschke, Sabina
Richert, Anja
Robotics
This paper investigates the impact of a group-adaptive conversation design in two socially interactive agents (SIAs) through two real-world studies. Both SIAs - Furhat, a social robot, and MetaHuman, a virtual agent - were equipped with a conversational artificial intelligence (CAI) backend combining hybrid retrieval and generative models. The studies were carried out in an in-the-wild setting with a total of $N = 188$ participants who interacted with the SIAs - in dyads, triads or larger groups - at a German museum. Although the results did not reveal a significant effect of the group-sensitive conversation design on perceived satisfaction, the findings provide valuable insights into the challenges of adapting CAI for multi-party interactions and across different embodiments (robot vs.\ virtual agent), highlighting the need for multimodal strategies beyond linguistic pluralization. These insights contribute to the fields of Human-Agent Interaction (HAI), Human-Robot Interaction (HRI), and broader Human-Machine Interaction (HMI), providing insights for future research on effective dialogue adaptation in group settings.
title Are We Generalizing from the Exception? An In-the-Wild Study on Group-Sensitive Conversation Design in Human-Agent Interactions
topic Robotics
url https://arxiv.org/abs/2506.10462