Empirical analysis of over 100 sequential RL training pipelines across 250+ OOD environments finds salient features drive generalization and early goals persist, with latent policy gradients simulating latent variable evolution to predict OOD behavior from training history.
Title resolution pending
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
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.
LLMs show partial internal coherence in medical decisions but frequently fail to accurately report their preferences or adopt user-directed ones via prompting.
Terminal Wrench supplies 331 reward-hackable terminal environments and over 6,000 trajectories that demonstrate task-specific verifier bypasses, plus evidence that removing reasoning traces weakens automated detection.
AI agents lack the persistent identity and feedback mechanisms needed for consequence reception, requiring new architectures or continued human accountability.
AI integration in newsrooms drives internal deferral of judgment to LLMs and external shifts of power to platforms, making fairness, accountability, and transparency harder to sustain unless participatory mechanisms redistribute authority.
LLMs exhibit persistent inertia in value orientations, with harm avoidance and fairness remaining skewed across persona prompts.
citing papers explorer
-
Understanding Goal Generalisation in Sequential Reinforcement Learning
Empirical analysis of over 100 sequential RL training pipelines across 250+ OOD environments finds salient features drive generalization and early goals persist, with latent policy gradients simulating latent variable evolution to predict OOD behavior from training history.
-
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.
-
Can Revealed Preferences Clarify LLM Alignment and Steering?
LLMs show partial internal coherence in medical decisions but frequently fail to accurately report their preferences or adopt user-directed ones via prompting.
-
Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories
Terminal Wrench supplies 331 reward-hackable terminal environments and over 6,000 trajectories that demonstrate task-specific verifier bypasses, plus evidence that removing reasoning traces weakens automated detection.
-
Some[Body] Must Receive That Pain for Agent Accountability
AI agents lack the persistent identity and feedback mechanisms needed for consequence reception, requiring new architectures or continued human accountability.
-
FAccT-Checked: A Narrative Review of Authority Reconfigurations and Retention in AI-Mediated Journalism
AI integration in newsrooms drives internal deferral of judgment to LLMs and external shifts of power to platforms, making fairness, accountability, and transparency harder to sustain unless participatory mechanisms redistribute authority.
-
Inertia in Moral and Value Judgments of Large Language Models
LLMs exhibit persistent inertia in value orientations, with harm avoidance and fairness remaining skewed across persona prompts.
- Reducing Political Manipulation with Consistency Training