EEG foundation models encode 68.6% of a 63-feature clinical lexicon in a representation-causal way, with frequency-domain features dominant; these recover 79.3% of the models' advantage over random baselines on average.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP) , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.
citing papers explorer
-
What Do EEG Foundation Models Capture from Human Brain Signals?
EEG foundation models encode 68.6% of a 63-feature clinical lexicon in a representation-causal way, with frequency-domain features dominant; these recover 79.3% of the models' advantage over random baselines on average.
-
Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles
H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.