Saved in:
Bibliographic Details
Main Authors: Zhang, Tong, Yang, X. Jessie, Li, Boyang
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2309.13965
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910562183544832
author Zhang, Tong
Yang, X. Jessie
Li, Boyang
author_facet Zhang, Tong
Yang, X. Jessie
Li, Boyang
contents Research in explainable AI (XAI) aims to provide insights into the decision-making process of opaque AI models. To date, most XAI methods offer one-off and static explanations, which cannot cater to the diverse backgrounds and understanding levels of users. With this paper, we investigate if free-form conversations can enhance users' comprehension of static explanations, improve acceptance and trust in the explanation methods, and facilitate human-AI collaboration. Participants are presented with static explanations, followed by a conversation with a human expert regarding the explanations. We measure the effect of the conversation on participants' ability to choose, from three machine learning models, the most accurate one based on explanations and their self-reported comprehension, acceptance, and trust. Empirical results show that conversations significantly improve comprehension, acceptance, trust, and collaboration. Our findings highlight the importance of customized model explanations in the format of free-form conversations and provide insights for the future design of conversational explanations.
format Preprint
id arxiv_https___arxiv_org_abs_2309_13965
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainability
Zhang, Tong
Yang, X. Jessie
Li, Boyang
Human-Computer Interaction
Artificial Intelligence
Research in explainable AI (XAI) aims to provide insights into the decision-making process of opaque AI models. To date, most XAI methods offer one-off and static explanations, which cannot cater to the diverse backgrounds and understanding levels of users. With this paper, we investigate if free-form conversations can enhance users' comprehension of static explanations, improve acceptance and trust in the explanation methods, and facilitate human-AI collaboration. Participants are presented with static explanations, followed by a conversation with a human expert regarding the explanations. We measure the effect of the conversation on participants' ability to choose, from three machine learning models, the most accurate one based on explanations and their self-reported comprehension, acceptance, and trust. Empirical results show that conversations significantly improve comprehension, acceptance, trust, and collaboration. Our findings highlight the importance of customized model explanations in the format of free-form conversations and provide insights for the future design of conversational explanations.
title May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainability
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2309.13965