Linear probes on residual-stream activations identify a shared preference vector in LLMs that tracks choices across prompts and causally steers decisions even for anti-correlated personas.
Will ai tell lies to save sick children? litmus-testing ai values prioritization with airiskdilemmas
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
LLMs exhibit pseudo-deliberation, with consistent value-action misalignment in generated dialogues despite reasoning, as measured by the new VALDI framework across 4941 scenarios.
A methodology to derive targeted Loss of Control mitigations by backchaining from AI errors on national security benchmarks to specific affordances and permissions.
LLMs align decisions with prescriptive moral rightness over loyalty-shifting human behavior predictions in relational moral dilemmas, revealing a gap between internal world-modeling and autonomous choices.
citing papers explorer
-
Probing Persona-Dependent Preferences in Language Models
Linear probes on residual-stream activations identify a shared preference vector in LLMs that tracks choices across prompts and causally steers decisions even for anti-correlated personas.
-
Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions
LLMs exhibit pseudo-deliberation, with consistent value-action misalignment in generated dialogues despite reasoning, as measured by the new VALDI framework across 4941 scenarios.
-
Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security
A methodology to derive targeted Loss of Control mitigations by backchaining from AI errors on national security benchmarks to specific affordances and permissions.
-
Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions
LLMs align decisions with prescriptive moral rightness over loyalty-shifting human behavior predictions in relational moral dilemmas, revealing a gap between internal world-modeling and autonomous choices.