6 citations · 6 across the 10 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?
Philippe Chlenski, Zachariah Carmichael, Ayush Warikoo +5
Mechanistic interpretability (MI) requires full access to model internals, yet the APIs for most widely deployed language models at best expose log-probabilities over output tokens…
cs.LG2026
Objective-Specific Privileged Bases via Full-Prefix Matryoshka Learning
Arghamitra Talukder, Philippe Chlenski, Itsik Pe'er
Learned representations are often invariant to rotational transformations, leaving individual dimensions non-identifiable and interchangeable. We study how Matryoshka Representatio…