Persona-Conditioned Generation

Follow this topic Ask about this topic

Persona-conditioned generation studies how profiles, personality traits, preferences, and behavioral histories can shape an AI system’s responses and actions. Common approaches include persona prompts and structured profiles, retrieval and memory, fine-tuning with adapters, and activation steering or decoding-time control. Applications range from role-playing dialogue and personalized text or images to speech, motion, survey simulation, and simulated users for agent testing; evaluations measure persona fidelity, preference alignment, behavioral diversity, and task performance. A central challenge is that richer persona descriptions do not always improve fidelity, while stronger conditioning can alter unrelated attributes, reduce accuracy, or reproduce bias.

Latest papers

109 papers17 papers in the last four weeks, up 21% on the four weeks before. 0.1% of all new papers.

Personality Latents: Conditioning Frozen Language Models on Individuals from Their Own Writing
Oct 27, 2026Gunhee Cho, Yun-Gyung CheongPersonality Modeling in Language Models Personalized Language Models
Dept. of AI, Sungkyunkwan University
Useful Diversity or Hallucinated Variety? Persona-Conditioned Synthetic Query Generation for E-Commerce Search
Oct 26, 2026Filippos Ventirozos, Tom Armitage, Mahmoud Oshagh +2E-Commerce Search Persona-Conditioned Generation
Manchester Metropolitan University, Manchester, UK · Autotrader UK, Manchester, UK
FATE-5: Faithful Alignment of Trait Expression for Continuous Big Five Personality Control
Oct 26, 2026Gunhee Cho, Hongyeob Kim, Yun-Gyung CheongPersonality Modeling in Language Models Personalized Language Model Alignment
Department of Artificial Intelligence, Sungkyunkwan University, Suwon, South Korea
Decoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation
Oct 23, 2026Qiyuan Li, Xiaomei Guo, Chao Gao +4Synthetic Clinical Data Generation Text Generation
School of Computer Science and Technology, Wuhan University of Science and Technology, China · Department of Cardiology, Tongji Hospital, Huazhong University of Science and Technology, China · Department of Computer Science, Vrije Universiteit Amsterdam, Netherlands +1
Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues
Oct 23, 2026Juan Li, Fangshu Chang, Xinyi Jiang +2User Simulation Synthetic Data Generation for LLM Agents
Bairong Inc.
A Thousand Faces: A Persuasion Benchmark with Experience-Grounded Persuadees Informed by Psychology and Pragmatics
Oct 18, 2026Ziqing Zhuang, Dingyi Zhang, Deyu ZhouPersuasion in Language Models Pragmatic Reasoning in Language Models
Southeast University
From Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations
Oct 12, 2026Dimitris Michailidis, Petter Törnberg, Fernando P. SantosLarge Language Model-Based Social Simulation Computational Social Science
Socially Intelligent Artificial Systems, University of Amsterdam · Institute for Logic, Language and Computation, University of Amsterdam
PersonaFactor: Preference Factors with Dynamic Selection for LLM Personalization
Oct 12, 2026Hang Su, Zequn Liu, Jianghan Chao +3LLM Personalization User Preference Modeling
East China Normal University · Beijing Zhongguancun Academy · Renmin University of China +1
Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution
Oct 7, 2026Masaaki Nakatsu, Reno WangLLM Inference LLM Context Management
AO, Inc. / OrbLabs AG · AO, Inc.
Wiki-Talkie: Multilingual Benchmarking of Persona-Based Agents on Real-World Discussions
Oct 6, 2026Dennis Fucci, Andrea Bacciu, Dong Liu +2Multilingual Language Model Evaluation Large Language Model-Based Role-Play Simulation
Amazon
Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes
Oct 5, 2026Dongryeol Lee, Weronika Łajewska, Leonardo Perelli +1Computational Social Science User Modeling
Seoul National University · Amazon
AgentPersonaBench: Benchmarking Persona-Driven User Simulation
Oct 3, 2026Jintao Huang, Yifan Wang, Hongyu Shen +43AI Agent Benchmarks Persona-Conditioned Generation
Behavioral History Outperforms Descriptions of the Person for LLM Synthetic Personas
Oct 2, 2026Khashayar Pourtaheri, Ahmad ZareeiLarge Language Model-Based Social Simulation Persona-Conditioned Generation
University of Washington · Berkeley
Personalized Image Generation with Reasoning and Reflection
Sep 30, 2026Bo Ni, Ngoc N. Tran, Qinwen Ge +10Image Generation Agentic Image Generation
Vanderbilt University · Adobe Systems · University of Maryland, College Park +1
LLM Persona Unlearning
Sep 30, 2026Kemou Li, Zhuan Shi, Qizhou Wang +4Model Editing Persona-Conditioned Generation
State Key Laboratory of Internet of Things for Smart City, University of Macau · Mila – Québec AI Institute · McGill University +3
Calibrated to Whom? Persona and Language Effects on Cultural Values in JEV
Sep 28, 2026Bushra Asseri, Abdulaziz AsseriMultilingual Language Model Evaluation Cross-Cultural Language Model Evaluation
College of Engineering and Advanced Computing, Alfaisal University, Riyadh, Saudi Arabia · Proxa.sa, Riyadh, Saudi Arabia
Persona Dosing: Calibrated Activation Steering for Graded Trait Control
Sep 28, 2026Zehao Jin, Junran Wang, Ruixuan Deng +4Language Model Steering Personality Modeling in Language Models
Georgia Institute of Technology · Zhejiang University · University of British Columbia
Persona Following Is Not Selective Control: The Neutrality Gap in LLM User Simulation
Sep 28, 2026Jiashen Ren, Wenlin Zhang, Bohan Zhang +5Persona-Conditioned Generation User Simulation
City University of Hong Kong · Stanford University
PersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona Representations
Sep 28, 2026Rui Xu, Yinghui Xu, Libo WuPersonality Modeling in Language Models Persona-Conditioned Generation
Fudan University · Shanghai Innovation Institute
OSPD: On-Policy Self-Distillation for Persona-Consistent Dialogue
Sep 28, 2026Rui Xu, Yikai Zhang, Aili Chen +3Large Language Model-Based Role-Play Simulation Persona Consistency
Fudan University · Shanghai Innovation Institute
Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs
Sep 24, 2026Sang Bin Moon, Nicole Cho, Daniel Borrajo +2Output Diversity in Language Models Diverse Text Generation
School of Electrical and Computer Engineering Purdue University West Lafayette, IN 47909, USA · J.P. Morgan AI Research New York, NY 10172, USA
Emergi-PersonaOS: A Persona Agent Operating System for Situational Adaptation and Controllable Evolution
Sep 23, 2026Haoluan Fu, Keni Chen, Xinyu Jia +3Persona Consistency Persona-Conditioned Generation
Emergi Lab of Qianzhen Digital Tech, China · Hangzhou Dianzi University, China
PERSONAWEAVER: Controllable Diversity Beyond Conventional Archetypes in Procedural Character Generation
Sep 22, 2026Maan Qraitem, Kate Saenko, Bryan A. PlummerPersonality Modeling in Language Models Procedural Content Generation
Boston University
Do Personality-Tuned LLMs Make Better Social Agents?
Sep 18, 2026Tim Krabbe, Xiaodan ShiLarge Language Model-Based Role-Play Simulation Persona-Conditioned Generation
Department of Computer and Systems Sciences, Stockholm University, 164 55, Kista, Sweden.
From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers
Sep 18, 2026Ji-Lun Peng, Yi-Zhen Zhang, Chun-Nan Chou +1Large Language Model-Based Role-Play Simulation Persona-Conditioned Generation
National Taiwan University, Taipei, Taiwan · CMoney Technology Corporation, Taiwan
ANIMASK: What the Model Contributes to Role Play in Simulated Story Worlds
Sep 15, 2026Xiucheng Zhang, Zhuoning Xu, Hanjun Luo +3Large Language Model-Based Role-Play Simulation Persona-Conditioned Generation
New York University · New York University Abu Dhabi · McGill University +1
I Am AdMan: A Pipeline for Automatic Generation of Personalized Advertising Imagery
Sep 11, 2026Victor Kolominsky-Rabas, Leopold Müller, Claudius Budcke +1Conditional Image Generation Image Generation
University of Bayreuth, Universitätsstraße 30, 95447 Bayreuth, Germany · Fraunhofer FIT, Wittelsbacherring 10, 95444 Bayreuth, Germany
A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation
Sep 8, 2026Rahul Khedar, Eshita, Sneha Teja Sree Reddy Thondapu +6LLM Agent Evaluation Multi-Turn Dialogue Evaluation
PayPal AI
Aegix Pulse: A Traceable Three-Stage Architecture for Personalized Content Generation and Context-Preserving Revision
Sep 7, 2026Hongnan Zhao, Shiyu Chen, Zhihao ChenLLM Personalization Evidence-Grounded Generation
1Aegix Insight
PTCG: Persona-guided Tree-based Counterargument Generation
Sep 7, 2026Eunbeen Son, Yohan Jo, Joonsuk Park +1Computational Argumentation Persuasion in Language Models
Sungkyunkwan University · Seoul National University · University of Richmond +1

Oct 27, 2026J/K move · Enter open · S save

Personality Latents: Conditioning Frozen Language Models on Individuals from Their Own Writing

Gunhee Cho, Yun-Gyung Cheong

Dept. of AI, Sungkyunkwan University

Personality Modeling in Language Models Personalized Language Models Persona-Conditioned Generation

Open paper AskPDF arXiv

Controlling the personality of a language model usually relies on written profiles or named trait categories, so it can only express what an author writes down or what a taxonomy names. We instead propose Personality Latents (PL), which learn a latent for each person from their own writing, with no personality labels and no authored profile, and inject it into a frozen language model as a soft prefix. Following generative latent optimization, each training person receives a free latent that is optimized through the frozen model itself, while an encoder learns to predict these latents so that a new person needs only one forward pass, with optional refinement at test time. We evaluate on held-out people by having the conditioned model answer neutral and interview questions and reading personality from its answers with scorers trained on real human writing. On the MBTI axes PL reaches an AUC of , ahead of persona embedding and prompt-based baselines under identical settings, and the ranking holds when the answers are scored in three different embedding spaces. A latent learned with Qwen2.5-3B-Instruct also transfers personality to Llama-3.1-8B-Instruct through a new adapter alone.