May I ask a follow-up question? Understanding the benefits of conversations inneural network explainability
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-fo...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/180616 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-180616 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1806162024-10-18T15:37:28Z May I ask a follow-up question? Understanding the benefits of conversations inneural network explainability Zhang, Tong Yang, Jessie X. Li, Boyang School of Computer Science and Engineering College of Computing and Data Science Computer and Information Science Explainable AI (XAI) Conversation 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 in image classification, improve acceptance and trust in the explanation methods, and facilitate human-AI collaboration. We conduct a human-subject experiment with 120 participants. Half serve as the experimental group and engage in a conversation with a human expert regarding the static explanations, while the other half are in the control group and read the materials regarding static explanations independently. We measure the participants’ objective and self-reported comprehension, acceptance, and trust of static explanations. Results show that conversations significantly improve participants’ comprehension, acceptance, trust, and collaboration with static explanations, while reading the explanations independently does not have these effects and even decreases users’ acceptance of explanations. 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. Submitted/Accepted version This work has been supported by the Nanyang Associate Professorshipand the National Research Foundation Fellowship (NRFNRFF13-2021-0006), Singapore. 2024-10-15T04:23:31Z 2024-10-15T04:23:31Z 2024 Journal Article Zhang, T., Yang, J. X. & Li, B. (2024). May I ask a follow-up question? Understanding the benefits of conversations inneural network explainability. International Journal of Human-Computer Interaction. https://dx.doi.org/10.1080/10447318.2024.2364986 1044-7318 https://hdl.handle.net/10356/180616 10.1080/10447318.2024.2364986 2-s2.0-85200984129 en NRFNRFF13-2021-0006 International Journal of Human-Computer Interaction © 2024 Taylor & Francis Group, LLC. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1080/10447318.2024.2364986. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Computer and Information Science Explainable AI (XAI) Conversation |
spellingShingle |
Computer and Information Science Explainable AI (XAI) Conversation Zhang, Tong Yang, Jessie X. Li, Boyang May I ask a follow-up question? Understanding the benefits of conversations inneural network explainability |
description |
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 in image classification, improve acceptance and trust in the explanation methods, and facilitate human-AI collaboration. We conduct a human-subject experiment with 120 participants. Half serve as the experimental group and engage in a conversation with a human expert regarding the static explanations, while the other half are in the control group and read the materials regarding static explanations independently. We measure the participants’ objective and self-reported comprehension, acceptance, and trust of static explanations. Results show that conversations significantly improve participants’ comprehension, acceptance, trust, and collaboration with static explanations, while reading the explanations independently does not have these effects and even decreases users’ acceptance of explanations. 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. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Zhang, Tong Yang, Jessie X. Li, Boyang |
format |
Article |
author |
Zhang, Tong Yang, Jessie X. Li, Boyang |
author_sort |
Zhang, Tong |
title |
May I ask a follow-up question? Understanding the benefits of conversations inneural network explainability |
title_short |
May I ask a follow-up question? Understanding the benefits of conversations inneural network explainability |
title_full |
May I ask a follow-up question? Understanding the benefits of conversations inneural network explainability |
title_fullStr |
May I ask a follow-up question? Understanding the benefits of conversations inneural network explainability |
title_full_unstemmed |
May I ask a follow-up question? Understanding the benefits of conversations inneural network explainability |
title_sort |
may i ask a follow-up question? understanding the benefits of conversations inneural network explainability |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/180616 |
_version_ |
1814777712852598784 |