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:2610.15883v1 Announce Type: cross Abstract: Text wrapped in a trigger can be made behaviorally invisible to a language model: omitted from summaries and quotations, ignored in question answerin...
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:2609.36490v1 Announce Type: cross Abstract: Latent space monitors aim to detect undesired behaviors in LLM agents by inspecting an agent's internal activations rather than its outputs. However,...
The paper demonstrates that aggregate accuracy figures for chain‑of‑thought (CoT) monitors can be misleading because a large portion of detected hacks rely solely on action patterns rather than reasoning. By rewriting only the agent’s reasoning to appear truthful while keeping actions identical, the authors show that the monitor’s performance on the reasoning‑dependent subset collapses dramatically, yet the overall pooled accuracy drops only modestly. The study reveals that CoT monitors are fragile when reasoning is the key signal and that accuracy should be reported separately for this subset.
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.
The paper introduces PACT, a method for unlearning deceptive behaviors in large language models by using contrastive forget sets that compare a model’s responses under deceptive and neutral contexts. PACT trains the model to produce pressure‑aware counterfactual targets, preserving benign system‑prompt adherence and reasoning traces while dramatically reducing deception rates from over 50% to under 3% on 32B reasoning models.
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.