Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

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

Publication

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

Feustel, Isabel; Rach, Niklas; Minker, Wolfgang; u. a. (2026): Enhancing Model Transparency : A Dialogue System Approach to XAI with Domain Knowledge, in: Bamberg: Otto-Friedrich-Universität, S. 248–258.

Details

Faculty/Chair
Faculty/Professorship
Author
Feustel, Isabel
Rach, Niklas
Minker, Wolfgang
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2026
Source/Other editions
Tatsuya Kawahara, Vera Demberg, Stefan Ultes, u. a. (Hrsg.), Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Kyoto: Association for Computational Linguistics, 2024, S. 248–258
Year of first publication
2024
Language
English
Licence
URN
Abstract

Explainable artifcial intelligence (XAI) is

a rapidly evolving feld that seeks to create

AI systems that can provide humanunderstandable

explanations for their decisionmaking

processes. However, these explanations

rely on model and data-specifc information

only. To support better human decisionmaking,

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 feld 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.

Keywords
-
Peer Reviewed
yes
International Distribution
yes
Type
Conferenceobject
URI
Activation date
2026-03-25

Permalink: https://fis.uni-bamberg.de/handle/uniba/114438 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-15

Restricted read-only access: login, editing and submission are temporarily disabled.