PersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona Representations
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/airaer1998/PersonaManifold
Sources
- Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Scaling Synthetic Data Creation with 1,000,000,000 Personas
- The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
- From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers
- Riemannian Continuous Normalizing Flows
- Dissecting Persona-Driven Reasoning in Language Models via Activation Patching
- Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data
- PersonaGym: Evaluating Persona Agents and LLMs
- Personality Vector: Modulating Personality of Large Language Models by Model Merging
- InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews
- CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulation
- MINDECHO: Role-Playing Language Agents for Key Opinion Leaders
- Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions?
- Your Language Model Secretly Contains Personality Subnetworks
- Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works
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