Predicting how model propensities generalize out of distribution
cs.AI, cs.CL, stat.ML
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/nielsrolf/propensity-spillover
Sources
- The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
- Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
- Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
- The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious
- Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
- Shortcut Learning in Deep Neural Networks
- Negation Neglect: When models fail to learn negations in training
- Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences
- Chunky Post-Training: Data Driven Failures of Generalization
- Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
- Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
- Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment
- Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
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