Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Multi-Agent AI Safety as an Institutional Design Problem
Abdullah X
AI agents increasingly work inside systems that govern how they delegate tasks, move information, execute actions, and use shared resources. Recent work already shows that deployme…
cs.LG2026
Markovian Circuit Tracing: Ground-Truth Tests of Transformer State Abstractions
Abdullah X
Mechanistic interpretability needs tests that separate accessible information from a causally useful internal abstraction. We introduce Markovian Circuit Tracing (MCT), a controlle…
cs.LG2025
Unlearning at Scale: State-Exact Trace-Preserving Deletion in Billion-Parameter Language Models
Abdullah X
Can a prospectively instrumented training continuation reproduce a deletion counterfactual exactly after selected examples leave its replay dataset? We study a trace-preserving cou…