From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP
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_ | 1866913131771461632 |
|---|---|
| author | Bexten, Justus Meyer zu Scherf, Nico Franczyk, Bogdan Hofmann, Simon M. |
| author_facet | Bexten, Justus Meyer zu Scherf, Nico Franczyk, Bogdan Hofmann, Simon M. |
| contents | Emerging foundation models (FMs) in electroencephalography (EEG) promise a path to scale deep learning in diagnostics and brain-computer interfaces despite data scarcity, yet their opaque nature remains a barrier to wider adoption. We investigate attention-aware Layer-wise relevance propagation (LRP) as a post-hoc attribution method for EEG-FMs, extending LRP's use on convolutional neural network (CNN)-based EEG models to the Transformer architectures that current FMs are based on. We find that LRP can both verify EEG-FM decisions and surface novel, biologically plausible hypotheses from them. In motor imagery, it unmasks 'Clever Hans' behavior where models prioritize task correlated ocular signals over the intended motor correlates. In a naturalistic paradigm for affect prediction, it reveals a recurring reliance on a central electrode cluster, suggesting a candidate sensorimotor signature of arousal. Though heatmap interpretation remains ambiguous in this complex domain, the results position LRP as a tool for both verification and exploration of EEG-FMs, a role that will grow in both importance and discovery potential as the underlying models mature. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11885 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP Bexten, Justus Meyer zu Scherf, Nico Franczyk, Bogdan Hofmann, Simon M. Artificial Intelligence Neurons and Cognition Emerging foundation models (FMs) in electroencephalography (EEG) promise a path to scale deep learning in diagnostics and brain-computer interfaces despite data scarcity, yet their opaque nature remains a barrier to wider adoption. We investigate attention-aware Layer-wise relevance propagation (LRP) as a post-hoc attribution method for EEG-FMs, extending LRP's use on convolutional neural network (CNN)-based EEG models to the Transformer architectures that current FMs are based on. We find that LRP can both verify EEG-FM decisions and surface novel, biologically plausible hypotheses from them. In motor imagery, it unmasks 'Clever Hans' behavior where models prioritize task correlated ocular signals over the intended motor correlates. In a naturalistic paradigm for affect prediction, it reveals a recurring reliance on a central electrode cluster, suggesting a candidate sensorimotor signature of arousal. Though heatmap interpretation remains ambiguous in this complex domain, the results position LRP as a tool for both verification and exploration of EEG-FMs, a role that will grow in both importance and discovery potential as the underlying models mature. |
| title | From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP |
| topic | Artificial Intelligence Neurons and Cognition |
| url | https://arxiv.org/abs/2605.11885 |