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.

Stories of Your Life as Others: A Round-Trip Evaluation of LLM-Generated Life Stories Conditioned on Rich Psychometric Profiles
Apr 7, 2026Ben Wigler, Maria Tsfasman, Tiffany Matej HrkalovicPersonality Modeling in Language Models Persona-Conditioned Generation
LoveMind AI · Jheronimus Academy of Data Science
PRCCF: A Persona-guided Retrieval and Causal-aware Cognitive Filtering Framework for Emotional Support Conversation
Apr 2, 2026Yanxin Luo, Xiaoyu Zhang, Jing Li +2Emotional Support Conversation Emotion-Aware Dialogue Generation
School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China · Oracle Cloud Infrastructure, Oracle, Santa Clara, CA, United States
Synonymix: Unified Group Personas for Generative Simulations
Mar 30, 2026Huanxing Chen, Aditesh KumarHuman Behavior Simulation Large Language Model-Based Social Simulation
Stanford University, Stanford, CA, USA
Persona-Based Simulation of Human Opinion at Population Scale
Mar 28, 2026Mao Li, Frederick G. ConradHuman Behavior Simulation Large Language Model-Based Social Simulation
Institute for Social Research, University of Michigan, 426 Thompson St., Ann Arbor, 48104, MI, US.
Analysing LLM Persona Generation and Fairness Interpretation in Polarised Geopolitical Contexts
Mar 24, 2026Maida Aizaz, Quang Minh NguyenPolitical Bias in Language Models Demographic Bias in Language Models
Graduate School of Data Science KAIST
Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM
Mar 19, 2026Zizhao Hu, Mohammad Rostami, Jesse ThomasonPersona-Conditioned Generation Personalized Language Model Alignment
University of Southern California Los Angeles, California, USA
Fusian: Multi-LoRA Fusion for Fine-Grained Continuous MBTI Personality Control in Large Language Models
Mar 16, 2026Zehao Chen, Rong PanPersonality Modeling in Language Models Persona-Conditioned Generation
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
Enhancing Debunking Effectiveness through LLM-based Personality Adaptation
Mar 10, 2026Pietro Dell'Oglio, Alessandro Bondielli, Francesco Marcelloni +1Persona-Conditioned Generation Persuasion in Language Models
Dipartimento di Ingegneria dell’Informazione, Università di Pisa, Largo Lucio Lazzarino 1, Pisa, Italy · Dipartimento di Informatica, Università di Pisa, Largo B. Pontecorvo 3, Pisa, Italy
Structured Style-Rewrite with Chain-of-Thought Planning for Low-Resource Character Dialogue
Mar 6, 2026Chanhui ZhuCoT Supervision Text Style Transfer
Guangdong University of Finance
HACHIMI: Scalable and Controllable Student Persona Generation via Orchestrated Agents
Mar 5, 2026Yilin Jiang, Fei Tan, Xuanyu Yin +2Synthetic Data Generation for Language Models Generative AI in Education
East China Normal University, Shanghai, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Shanghai Innovation Institute, Shanghai, China
Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
Mar 2, 2026Yuxin Liu, Mingye Zhu, Siyuan Liu +2Large Language Model-Based Role-Play Simulation Persona-Conditioned Generation
University of Science and Technology of China
Sydney Telling Fables on AI and Humans: A Corpus Tracing Memetic Transfer of Persona between LLMs
Feb 25, 2026Jiří Milička, Hana BednářováPersonality Modeling in Language Models Persona-Conditioned Generation
Charles University, Prague
InterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation
Feb 23, 2026Yu Li, Pranav Narayanan Venkit, Yada Pruksachatkun +1Personality Modeling in Language Models Human Behavior Simulation
Salesforce Research
Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs
Feb 22, 2026Wenqiu Tang, Zhen Wan, Takahiro Komamizu +1Persona-Conditioned Generation Large Language Model-Based Role-Play Simulation
Nagoya University, Nagoya, Aichi, Japan · Kyoto University, Kyoto, Japan
PsyCLIENT: Client Simulation via Conversational Trajectory Modeling for Trainee Practice and Model Evaluation in Mental Health Counseling
Jan 12, 2026Huachuan Qiu, Zhaoming Chen, Yuqian Chen +3Large Language Model-Based Role-Play Simulation User Simulation
Westlake University · The University of Utah
Iterative Critique-Refine Framework for Enhancing LLM Personalization
Oct 28, 2025Durga Prasad Maram, Dhruvin Gandhi, Zonghai Yao +5LLM Personalization Personalized Language Models
University of Massachusetts Amherst · Adobe Research · University of Oregon +1
Political Ideology Shifts in Large Language Models
Aug 22, 2025Pietro Bernardelle, Stefano Civelli, Leon Fröhling +3Political Bias in Language Models Language Model Bias Evaluation
The University of Queensland, Brisbane, Australia · GESIS, Cologne, Germany · University of Udine, Udine, Italy
Scaling Personality Control in LLMs with Big Five Scaler Prompts
Aug 8, 2025Gunhee Cho, Yun-Gyung CheongPersona-Conditioned Generation Controllable Text Generation
Sungkyunkwan University, South Korea
MotionPersona: Real-Time Locomotion Control across Personas, Bodies, and Styles
May 30, 2025Mingyi Shi, Wei Liu, Jidong Mei +4Human Motion Generation Motion Retargeting
The University of Hong Kong, Hong Kong · Shandong University, China · Hong Kong University of Science and Technology, Hong Kong +2

Apr 7, 2026J/K move · Enter open · S save

Stories of Your Life as Others: A Round-Trip Evaluation of LLM-Generated Life Stories Conditioned on Rich Psychometric Profiles

Ben Wigler, Maria Tsfasman, Tiffany Matej Hrkalovic

LoveMind AI · Jheronimus Academy of Data Science

Personality Modeling in Language Models Persona-Conditioned Generation Language Model Generation Evaluation

Open paper AskPDF arXiv

Personality traits are richly encoded in natural language, and large language models (LLMs) trained on human text can simulate personality when conditioned on persona descriptions. However, existing evaluations rely predominantly on questionnaire self-report by the conditioned model, are limited in architectural diversity, and rarely use real human psychometric data. Without addressing these limitations, it remains unclear whether personality conditioning produces psychometrically informative representations of individual differences or merely superficial alignment with trait descriptors. To test how robustly LLMs can encode personality into extended text, we condition LLMs on real psychometric profiles from 290 participants to generate first-person life story narratives, and then task independent LLMs to recover personality scores from those narratives alone. We show that personality scores can be recovered from the generated narratives at levels approaching human test-retest reliability (mean r = 0.750, 85% of the human ceiling), and that recovery is robust across 10 LLM narrative generators and 3 LLM personality scorers spanning 6 providers. Decomposing systematic biases reveals that scoring models achieve their accuracy while counteracting alignment-induced defaults. Content analysis of the generated narratives shows that personality conditioning produces behaviourally differentiated text: nine of ten coded features correlate significantly with the same features in participants' real conversations, and personality-driven emotional reactivity patterns in narratives replicate in real conversational data. These findings provide evidence that the personality-language relationship captured during pretraining supports robust encoding and decoding of individual differences, including characteristic emotional variability patterns that replicate in real human behaviour.