Persona Perspectives: Adopting Viewpoints Reorganizes Representations in LLMs
cs.CL
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- BatchTopK Sparse Autoencoders
- The Llama 3 Herd of Models
- Gemma 3 Technical Report
- Linear representations in language models can change dramatically over a conversation
- Ministral 3
- Priors in Time: Missing Inductive Biases for Language Model Interpretability
- Steering Llama 2 via Contrastive Activation Addition
- AI Simulations Grounded in Rich Self-Reports Increase Accuracy and Reduce Distortion
- The Linear Representation Hypothesis and the Geometry of Large Language Models
- Linear Representations of Sentiment in Large Language Models
- Persona Features Control Emergent Misalignment
- Qwen3 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