Is Persona Generalization Predictable?
cs.CL, cs.LG
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/olimu/persona-generalization
Terminology
Sources
- Invariant Risk Minimization
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
- The Llama 3 Herd of Models
- Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
- Olmo 3
- Steering Language Models with Weight Arithmetic
- Natural Emergent Misalignment from Reward Hacking in Production RL
- Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow Finetuning
- From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs
- Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
- Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
- Convergent Linear Representations of Emergent Misalignment
- Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
- Model Organisms for Emergent Misalignment
- Persona Features Control Emergent Misalignment
- Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
- Robust fine-tuning of zero-shot models
- Qwen2.5 Technical Report
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data