11 citations · 11 across the 5 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors
Maheep Chaudhary, Fazl Barez
White-box monitoring is increasingly adopted as an auditing tool as Large Language Models (LLMs) are deployed in daily operations to ensure safe model behavior. However, white-box…
cs.AI2023★ 11 cited
Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
Atticus Geiger, Duligur Ibeling, Amir Zur +8
Causal abstraction provides a theoretical foundation for mechanistic interpretability, the field concerned with providing intelligible algorithms that are faithful simplifications…