Attention layers in tabular foundation models enable effective membership inference attacks via pattern concentration, addressed by an inference-time k-anonymity defense on high-risk queries that cuts leakage by ~50% with minimal utility loss.
In-context learning for extreme multi-label classification,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Reasoning in large output spaces proceeds via shortlisting then fine-grained reasoning; this characterization enables a mechanistic distillation strategy that outperforms standard distillation.
citing papers explorer
-
Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries
Attention layers in tabular foundation models enable effective membership inference attacks via pattern concentration, addressed by an inference-time k-anonymity defense on high-risk queries that cuts leakage by ~50% with minimal utility loss.
-
Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces
Reasoning in large output spaces proceeds via shortlisting then fine-grained reasoning; this characterization enables a mechanistic distillation strategy that outperforms standard distillation.