Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria
cs.AI
Submitted: 2025-11-22
Updated: 2026-10-10
Terminology
Sources
- GPT-4 Technical Report
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- Constitutional AI: Harmlessness from AI Feedback
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Alignment faking in large language models
- The Curious Case of Neural Text Degeneration
- Risks from Learned Optimization in Advanced Machine Learning Systems
- PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
- Why Language Models Hallucinate
- From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
- Categorizing Variants of Goodhart's Law
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- Evaluation Awareness Scales Predictably in Open-Weights Large Language Models
- Training language models to follow instructions with human feedback
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Are Emergent Abilities of Large Language Models a Mirage?
- Why Do Some Language Models Fake Alignment While Others Don't?
- HelpSteer2-Preference: Complementing Ratings with Preferences
- Emergent Abilities of Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems