Enhancing XAI Interpretation through a Reverse Mapping from Insights to Visualizations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914005862318080 |
|---|---|
| author | Nuthalapati, Aniket Hinds, Nicholas Lim, Brian Y. Wang, Qianwen |
| author_facet | Nuthalapati, Aniket Hinds, Nicholas Lim, Brian Y. Wang, Qianwen |
| contents | As AI systems become increasingly integrated into high-stakes domains, enabling users to accurately interpret model behavior is critical. While AI explanations can be provided, users often struggle to reason effectively with these explanations, limiting their ability to validate or learn from AI decisions. To address this gap, we introduce Reverse Mapping, a novel approach that enhances visual explanations by incorporating user-derived insights back into the explanation workflow. Our system extracts structured insights from free-form user interpretations using a large language model and maps them back onto visual explanations through interactive annotations and coordinated multi-view visualizations. Inspired by the verification loop in the visualization knowledge generation model, this design aims to foster more deliberate, reflective interaction with AI explanations. We demonstrate our approach in a prototype system with two use cases and qualitative user feedback. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18640 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing XAI Interpretation through a Reverse Mapping from Insights to Visualizations Nuthalapati, Aniket Hinds, Nicholas Lim, Brian Y. Wang, Qianwen Human-Computer Interaction As AI systems become increasingly integrated into high-stakes domains, enabling users to accurately interpret model behavior is critical. While AI explanations can be provided, users often struggle to reason effectively with these explanations, limiting their ability to validate or learn from AI decisions. To address this gap, we introduce Reverse Mapping, a novel approach that enhances visual explanations by incorporating user-derived insights back into the explanation workflow. Our system extracts structured insights from free-form user interpretations using a large language model and maps them back onto visual explanations through interactive annotations and coordinated multi-view visualizations. Inspired by the verification loop in the visualization knowledge generation model, this design aims to foster more deliberate, reflective interaction with AI explanations. We demonstrate our approach in a prototype system with two use cases and qualitative user feedback. |
| title | Enhancing XAI Interpretation through a Reverse Mapping from Insights to Visualizations |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2508.18640 |