Localizing and Editing the Goal Representation of a Vision-Language-Action Model
Overview
This research investigates how OpenVLA handles safety prohibitions by analyzing its internal goal representations. Using activation patching, linear probes, and runtime monitors on the LIBERO-Goal benchmark, the authors find that negation instructions have no detectable effect on task execution in the base model. The study identifies that steering vectors at layer 8 can redirect behavior, while effective goal editing requires intervention before layer 12 or patching every decoded action token starting from layer 16. External probes combining image and instruction features perform comparably to internal failure detectors for detecting non-compliance.
Generated from attributed reports · Updated 26 minutes ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalLocalizing and Editing the Goal Representation of a Vision-Language-Action Model
This research investigates how OpenVLA handles safety prohibitions by analyzing its internal goal representations. Using activation patching, linear probes, and runtime monitors on the LIBERO-Goal benchmark, the authors find that negation instructions have no detectable effect on task execution in the base model. The study identifies that steering vectors at layer 8 can redirect behavior, while effective goal editing requires intervention before layer 12 or patching every decoded action token starting from layer 16. External probes combining image and instruction features perform comparably to internal failure detectors for detecting non-compliance.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).