CIF certifies interventional interpretability metrics as bounded causal means with anytime-valid confidence sequences, including under adaptive sampling, cutting certification cost 10–30× with betting sequences.
Advances in Neural Information Processing Systems , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
ICL task identity is encoded as distributed output format templates across demonstration tokens rather than localized at single positions.
citing papers explorer
-
Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability
CIF certifies interventional interpretability metrics as bounded causal means with anytime-valid confidence sequences, including under adaptive sampling, cutting certification cost 10–30× with betting sequences.
-
Single-Position Intervention Fails: Distributed Output Templates Drive In-Context Learning
ICL task identity is encoded as distributed output format templates across demonstration tokens rather than localized at single positions.