When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs
Paper • 2609.36138 • Published • 6
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs
See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs
rzdiversity
submitted a
paper to Daily Papers 3 days ago
rzdiversity
submitted a
paper to Daily Papers 5 days ago