How Far Do Persona Effects Generalize in Language Models?
cs.CL, cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/thzva/persona-gain
Terminology
Sources
- How Well Do Large Language Models Capture Human Personality?
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- When Persona Attributes Improve Population Alignment in Large Language Models
- Diagnosing and Repairing Persona Collapse in LLM Advice
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
- Generative Agents: Interactive Simulacra of Human Behavior
- LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
- German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies
- Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
- Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability
- Persona Features Control Emergent Misalignment
- DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas
- The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering