arXiv:2608.29956v1 Announce Type: new Abstract: Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete p...
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.
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:2608. 04735v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is increasingly treated as an important safety layer for frontier reasoning models.
arXiv:2608. 02089v1 Announce Type: new Abstract: Large language models often show users a final response and a short reasoning summary while the full reasoning trace stays hidden.
arXiv:2607. 08173v1 Announce Type: new Abstract: Black box auditing of language models is an essential pre-deployment tool, but it may miss subtle forms of misalignment and hidden information.
arXiv:2607. 03598v1 Announce Type: cross Abstract: When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by sending it: share a finished project and it critiques the code; share a raw late-night line and it runs a wellness check.
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
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. 29441v1 Announce Type: cross Abstract: Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists.
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.
arXiv:2608.02657v2 Announce Type: replace-cross Abstract: Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.g., malicious side-tasks hidden in external tool results. While man...