TA
Tomer Ashuach
cs.CL
On Valency
published · living versionsW_7vj6bpzm·v1 · currentpublished
The Geometry of Ignorance: Detecting Suppressed Knowledge in LLMs through Activation Fragmentation
with Adar Peleg, Dvir Alsheich, Avi Mendelson
1 version
Preprints & journals
4 papers in the corpus · 2024–2026Reasoning Models Know What's Important, and Encode It in Their Activations2604.18307v2 · Yaniv Nikankin, Martin Tutek, Tomer Ashuach et al.2026 · 1 citationarXiv
Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness2604.12373v5 · Tomer Ashuach, Shai Gretz, Yoav Katz et al.2026 · 0 citationsarXiv
CRISP: Persistent Concept Unlearning via Sparse Autoencoders2508.13650v3 · Tomer Ashuach, Dana Arad, Aaron Mueller et al.2025 · 0 citationsarXiv
REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space2406.09325v6 · Tomer Ashuach, Martin Tutek, Yonatan Belinkov2024 · 1 citationarXiv
Career total: 7 works. 4 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.