Can Conversational XAI Improve User Performance? An Experimental Study
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910239166562304 |
|---|---|
| author | Kruschel, Sven Rosenberger, Julian Bohlen, Lasse Kraus, Mathias Zschech, Patrick |
| author_facet | Kruschel, Sven Rosenberger, Julian Bohlen, Lasse Kraus, Mathias Zschech, Patrick |
| contents | Explainable AI (XAI) techniques aim to provide insights into predictive models and enhance user performance, yet they often fall short of these expectations. Conversational XAI assistants promise to overcome such limitations, but empirical evidence on their impact on objective performance measures remains limited. We propose an experimental design for evaluating explanation assistance through prediction accuracy, model understanding, and error identification. Using an explainable-by-design prediction model, we create conditions where users can outperform the model by identifying and compensating for systematic errors. We compare conversational assistance against Q&A-based assistance to assess which better supports users in working with model explanations. Preliminary results from testing our experimental design show that participants (N=42) in both treatments significantly outperformed the model but reveal no performance differences between assistance types and modest engagement overall. These findings inform refinements for our planned full study, including enhanced engagement interventions and investigation of the mechanisms driving improved predictions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_20439 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Can Conversational XAI Improve User Performance? An Experimental Study Kruschel, Sven Rosenberger, Julian Bohlen, Lasse Kraus, Mathias Zschech, Patrick Machine Learning Human-Computer Interaction Explainable AI (XAI) techniques aim to provide insights into predictive models and enhance user performance, yet they often fall short of these expectations. Conversational XAI assistants promise to overcome such limitations, but empirical evidence on their impact on objective performance measures remains limited. We propose an experimental design for evaluating explanation assistance through prediction accuracy, model understanding, and error identification. Using an explainable-by-design prediction model, we create conditions where users can outperform the model by identifying and compensating for systematic errors. We compare conversational assistance against Q&A-based assistance to assess which better supports users in working with model explanations. Preliminary results from testing our experimental design show that participants (N=42) in both treatments significantly outperformed the model but reveal no performance differences between assistance types and modest engagement overall. These findings inform refinements for our planned full study, including enhanced engagement interventions and investigation of the mechanisms driving improved predictions. |
| title | Can Conversational XAI Improve User Performance? An Experimental Study |
| topic | Machine Learning Human-Computer Interaction |
| url | https://arxiv.org/abs/2605.20439 |