Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.04841 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917248299433984 |
|---|---|
| author | Rhee, Jeongmin Lee, Changhee Shin, DongHwa Kim, Bohyoung |
| author_facet | Rhee, Jeongmin Lee, Changhee Shin, DongHwa Kim, Bohyoung |
| contents | Explainable Artificial Intelligence (XAI) has gained importance in interpreting model predictions. Among leading techniques for XAI, Local Interpretable Model-agnostic Explanations (LIME) is most frequently utilized as it notably helps people's understanding of complex models. However, LIME's analysis is constrained to a single image at a time. Besides, it lacks interaction mechanisms for observing the LIME's results and direct manipulations of factors affecting the results. To address these issues, we introduce an interactive visualization tool, LIMEVis, which improves the analysis workflow of LIME by enabling users to explore multiple LIME results simultaneously and modify them directly. With LIMEVis, we could conveniently identify common features in images that a model seems to mainly consider for category classification. Additionally, by interactively modifying the LIME results, we could determine which segments in an image influence the model's classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04841 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Vivifying LIME: Visual Interactive Testbed for LIME Analysis Rhee, Jeongmin Lee, Changhee Shin, DongHwa Kim, Bohyoung Human-Computer Interaction Explainable Artificial Intelligence (XAI) has gained importance in interpreting model predictions. Among leading techniques for XAI, Local Interpretable Model-agnostic Explanations (LIME) is most frequently utilized as it notably helps people's understanding of complex models. However, LIME's analysis is constrained to a single image at a time. Besides, it lacks interaction mechanisms for observing the LIME's results and direct manipulations of factors affecting the results. To address these issues, we introduce an interactive visualization tool, LIMEVis, which improves the analysis workflow of LIME by enabling users to explore multiple LIME results simultaneously and modify them directly. With LIMEVis, we could conveniently identify common features in images that a model seems to mainly consider for category classification. Additionally, by interactively modifying the LIME results, we could determine which segments in an image influence the model's classification. |
| title | Vivifying LIME: Visual Interactive Testbed for LIME Analysis |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2602.04841 |