[go: up one dir, main page]

Enhancing Model Transparency: A Dialogue System Approach to XAI with Domain Knowledge

Isabel Feustel, Niklas Rach, Wolfgang Minker, Stefan Ultes


Abstract
Explainable artificial intelligence (XAI) is a rapidly evolving field that seeks to create AI systems that can provide human-understandable explanations for their decision-making processes. However, these explanations rely on model and data-specific information only. To support better human decision-making, integrating domain knowledge into AI systems is expected to enhance understanding and transparency. In this paper, we present an approach for combining XAI explanations with domain knowledge within a dialogue system. We concentrate on techniques derived from the field of computational argumentation to incorporate domain knowledge and corresponding explanations into human-machine dialogue. We implement the approach in a prototype system for an initial user evaluation, where users interacted with the dialogue system to receive predictions from an underlying AI model. The participants were able to explore different types of explanations and domain knowledge. Our results indicate that users tend to more effectively evaluate model performance when domain knowledge is integrated. On the other hand, we found that domain knowledge was not frequently requested by the user during dialogue interactions.
Anthology ID:
2024.sigdial-1.22
Volume:
Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2024
Address:
Kyoto, Japan
Editors:
Tatsuya Kawahara, Vera Demberg, Stefan Ultes, Koji Inoue, Shikib Mehri, David Howcroft, Kazunori Komatani
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
248–258
Language:
URL:
https://aclanthology.org/2024.sigdial-1.22
DOI:
10.18653/v1/2024.sigdial-1.22
Bibkey:
Cite (ACL):
Isabel Feustel, Niklas Rach, Wolfgang Minker, and Stefan Ultes. 2024. Enhancing Model Transparency: A Dialogue System Approach to XAI with Domain Knowledge. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 248–258, Kyoto, Japan. Association for Computational Linguistics.
Cite (Informal):
Enhancing Model Transparency: A Dialogue System Approach to XAI with Domain Knowledge (Feustel et al., SIGDIAL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sigdial-1.22.pdf