Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.02720 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917059913318400 |
|---|---|
| author | Kůr, Vojtěch Bajger, Adam Kukučka, Adam Hradil, Marek Musil, Vít Brázdil, Tomáš |
| author_facet | Kůr, Vojtěch Bajger, Adam Kukučka, Adam Hradil, Marek Musil, Vít Brázdil, Tomáš |
| contents | Convolutional neural networks (CNNs) underpin many modern computer vision systems. With applications ranging from common to critical areas, a need to explain and understand the model and its decisions (XAI) emerged. Prior works suggest that in the top layers of CNNs, the individual channels can be attributed to classifying human-understandable concepts. Concept relevance propagation (CRP) methods can backtrack predictions to these channels and find images that most activate these channels. However, current CRP workflows are largely manual: experts must inspect activation images to name the discovered concepts and must synthesize verbose explanations from relevance maps, limiting the accessibility of the explanations and their scalability.
To address these issues, we introduce Large Language model EXplaIns COncept Relevance Propagation (LLEXICORP), a modular pipeline that couples CRP with a multimodal large language model. Our approach automatically assigns descriptive names to concept prototypes and generates natural-language explanations that translate quantitative relevance distributions into intuitive narratives. To ensure faithfulness, we craft prompts that teach the language model the semantics of CRP through examples and enforce a separation between naming and explanation tasks. The resulting text can be tailored to different audiences, offering low-level technical descriptions for experts and high-level summaries for non-technical stakeholders.
We qualitatively evaluate our method on various images from ImageNet on a VGG16 model. Our findings suggest that integrating concept-based attribution methods with large language models can significantly lower the barrier to interpreting deep neural networks, paving the way for more transparent AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02720 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLEXICORP: End-user Explainability of Convolutional Neural Networks Kůr, Vojtěch Bajger, Adam Kukučka, Adam Hradil, Marek Musil, Vít Brázdil, Tomáš Computer Vision and Pattern Recognition Artificial Intelligence Convolutional neural networks (CNNs) underpin many modern computer vision systems. With applications ranging from common to critical areas, a need to explain and understand the model and its decisions (XAI) emerged. Prior works suggest that in the top layers of CNNs, the individual channels can be attributed to classifying human-understandable concepts. Concept relevance propagation (CRP) methods can backtrack predictions to these channels and find images that most activate these channels. However, current CRP workflows are largely manual: experts must inspect activation images to name the discovered concepts and must synthesize verbose explanations from relevance maps, limiting the accessibility of the explanations and their scalability. To address these issues, we introduce Large Language model EXplaIns COncept Relevance Propagation (LLEXICORP), a modular pipeline that couples CRP with a multimodal large language model. Our approach automatically assigns descriptive names to concept prototypes and generates natural-language explanations that translate quantitative relevance distributions into intuitive narratives. To ensure faithfulness, we craft prompts that teach the language model the semantics of CRP through examples and enforce a separation between naming and explanation tasks. The resulting text can be tailored to different audiences, offering low-level technical descriptions for experts and high-level summaries for non-technical stakeholders. We qualitatively evaluate our method on various images from ImageNet on a VGG16 model. Our findings suggest that integrating concept-based attribution methods with large language models can significantly lower the barrier to interpreting deep neural networks, paving the way for more transparent AI systems. |
| title | LLEXICORP: End-user Explainability of Convolutional Neural Networks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.02720 |