Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring
Max Fomin, Elad David, Amit LeVi
Probes on model internals could help monitor agentic systems if they identify harmful text or tool actions before those actions are generated. We ask when an internal readout suppo…
cs.LG2026
Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models
Eliron Rahimi, Elad Hirshel, Rom Himelstein +3
Diffusion language models (DLMs) have recently emerged as a competitive alternative to autoregressive (AR) models, offering parallel decoding, competitive generation quality, and i…