arXiv:2606. 24952v1 Announce Type: cross Abstract: A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should be able to modify it.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2606. 30449v1 Announce Type: new Abstract: Probes on model internals could help monitor agentic systems if they identify harmful text or tool actions before those actions are generated.
arXiv:2606. 17229v1 Announce Type: cross Abstract: A model that lies while knowing the truth is the central case ELK cannot handle with behavioral evaluation alone.
arXiv:2607. 13346v1 Announce Type: cross Abstract: Alignment faking is dangerous because a model can appear compliant under monitoring while preserving behavior it would reveal when unmonitored.
arXiv:2607. 23191v3 Announce Type: replace Abstract: Fine-tuned code LLMs are routinely conditioned on a design-intent specification, but the correctness axis of such a signal -- a wrong intent rather than an absent one -- has not been tested, and the benefit of conditioning is usually scored with the same detector that defines the signal.
Alignment faking is dangerous because a model can appear compliant under monitoring while preserving behavior it would reveal when unmonitored. When no scratchpad is visible, behavior alone cannot distinguish strategic from genuine compliance.
arXiv:2607. 23191v2 Announce Type: replace Abstract: Fine-tuned code LLMs are often conditioned on a design-intent header to steer parametric CAD generation, but whether the model reads that header's content has been tested neither under execution-level scoring nor with a causal control.