From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research
cs.AI
Submitted: 2026-09-03
Updated: 2026-09-03
Code: https://github.com/yshk-mxim/deceptive-mechanism
Terminology
Sources
- Probing the Lack of Stable Internal Beliefs in LLMs
- Discovering Latent Knowledge in Language Models Without Supervision
- "Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms
- Large Language Models can Strategically Deceive their Users when Put Under Pressure
- AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Measuring Faithfulness in Chain-of-Thought Reasoning
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection