Concept-based models can use controlled 'benign' information leakage to remain accurate and intervenable under real-world concept incompleteness by reframing their training objective.
arXiv preprint arXiv:2310.10702 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
In Defense of Information Leakage in Concept-based Models
Concept-based models can use controlled 'benign' information leakage to remain accurate and intervenable under real-world concept incompleteness by reframing their training objective.