A VQ-based gated Transformer trained on AG News produces symbol traces that are supposed to be interpretable, but accuracy is low (50.94% then 47.32%) and central results are unreported.
A Survey of Methods for Explaining Black Box Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Interpretable by AI Mother Tongue: Native Symbolic Reasoning in Neural Models
A VQ-based gated Transformer trained on AG News produces symbol traces that are supposed to be interpretable, but accuracy is low (50.94% then 47.32%) and central results are unreported.