Persona Prompting

Follow this topic Ask about this topic

Persona prompting studies how descriptions of a model’s role, background, values, or preferences can steer its answers, recommendations, and decisions. Common approaches include expert-role prompts, personas grounded in survey data, and retrieval methods that select relevant roles; evaluations span survey prediction, recommendation, bias audits, and multimodal tasks. Persona prompts can shift outputs, but effects vary by model and task, and gains in one measure may come with costs in clarity, factuality, or diversity. A central open question is whether prompts produce reliable, human-faithful behavior or mainly alter surface wording without changing underlying biases or preferences.

Latest papers

23 papers1 paper in the last four weeks, down 75% on the four weeks before. 0.0% of all new papers.

A Large-Scale Evaluation of Role-Enhanced Zero-Shot Chain-of-Thought Prompting
Oct 21, 2026Ibrahim Khan, Thai Van Nguyen, Yi Xia +5LLM Prompting Adaptive Reasoning in Language Models
College of Information Science and Technology, Ritsumeikan University, Japan · Graduate School of Information Science and Technology, Ritsumeikan University, Japan · Independent Researcher, and an alumnus of the Graduate School of Information Science and Technology, Ritsumeikan University, Japan +1
Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30
Sep 18, 2026Hans Andersen, David DichasLanguage Model Steering Moral Reasoning in Language Models
Navigating the digital spectrum: Assessing political bias, stability, and downstream fairness in Large Language Models
Sep 8, 2026Luka Debevc, Nishan Chatterjee, Antoine Doucet +2Multilingual Language Model Evaluation Political Bias in Language Models
1Jožef Stefan Institute, Ljubljana, Slovenia · University of Ljubljana, Ljubljana, Slovenia · 2Jožef Stefan International Postgraduate School, Ljubljana, Slovenia +1
The Illusion of Debiasing: Persona Steering Redistributes Rather Than Reduces Bias in LLMs
Sep 7, 2026Ziyue Feng, Hongbo Fang, James A. EvansLanguage Model Steering Language Model Debiasing
University of Chicago Chicago, IL, USA
When Persona Attributes Improve Population Alignment in Large Language Models
Sep 2, 2026Leon Fröhling, Jens Rupprecht, Markus Strohmaier +1Persona Prompting
GESIS – Leibniz Institute for the Social Sciences · University of Mannheim · Complexity Science Hub +1
Chehre: An Emoji-Prompted Dataset to Explore Perceptual Flexibility in Video Language Models
Jun 19, 2026Bita Azari, Zoe Stanley, Avneet Batra +4VLM Evaluation Video-Language Model Evaluation
Simon Fraser University, Canada
Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI Models
Jun 16, 2026Jasmine Brazilek, Joel Christoph, Maheep Chaudhary +4AI Agent Evaluation AI Agent Safety
CaML · Harvard Kennedy School · Sentient Futures +1
ZIPP:Zero-shot Image Personalization from Personas
Jun 7, 2026Harini SI, Somesh Singh, Yaman Kumar Singla +2T2I Generation Persona Prompting
Adobe Media and Data Science Research (MDSR) · SUNY at Buffalo · IIIT-Delhi
Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations
Jun 4, 2026Salvatore Greco, Hainiu Xu, Jacopo Domenicucci +2Moral Reasoning in Language Models AI Alignment
Centre for Data Futures, The Dickson Poon School of Law, King’s College London · Department of Informatics, King’s College London · LangAI, Center for Language AI Research, Tohoku University +1
The Assistant as a Privileged Persona: A canonical reference in cross-persona self-recognition
May 30, 2026Asvin GPersonality Modeling in Language Models Authorship Attribution
Institute for Advanced Study, Princeton
Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider Audit
May 28, 2026Will Jack, Noah Lehman, Keller Maloney +1LLM Personalization Recommender Systems
Unusual
When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs
May 28, 2026Shuai Xiao, Su Liu, Weikai Zhou +4LLM Evaluation LLM Prompting
Independent Researchers
Persona Prompting in Multimodal Urban Perception: Descriptive Convergence and Interpretive Variation
May 27, 2026Neemias da Silva, Matt Ratto, Myriam Delgado +3Multimodal Large Language Models Language Model Bias Evaluation
University of Toronto, Toronto, Canada · Universidade Tecnologica Federal do Parana, Curitiba, Brazil
Whose Name Comes Up? III: Persona Prompting Effects in LLM-Based Scholar Recommendation
May 27, 2026Annabella Sánchez-Guzmán, Lukas Eberhard, Denis Helic +1LLM Auditing LLM Prompting
Escuela Superior Polit´ecnica del Litoral · Graz University of Technology · Complexity Science Hub
As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs
May 22, 2026Eric XuLLM Prompting LLM Interpretability
Independent Researcher
Philosophical Dispositions as Behavioral Constraints for AI-Assisted Code Review: An Empirical Study
May 21, 2026Kaushal BansalPersona Prompting Automated Code Review
Salesforce, Inc. San Francisco, CA, USA
Improving Cross-Cultural Survey Simulation with Calibrated Value Personas
May 15, 2026Axel Abels, Elias Fernandez Domingos, Apurva Shah +1Language Model Calibration Cultural Bias in Language Models
1Machine Learning Group, Universit´e Libre de Bruxelles · 2AI Lab, Vrije Universiteit Brussel · 3FARI Institute, Universit´e Libre de Bruxelles - Vrije Universiteit Brussel +2
Probing Persona-Dependent Preferences in Language Models
May 13, 2026Oscar Gilg, Pierre Beckmann, Daniel Paleka +1LLM Alignment LLM Interpretability
MATS · MATS, EPFL · ETH Zürich +1
Dynamic In-Group Persona Generation for Enhancing Human-AI Rapport
May 5, 2026Yoonseok Oh, Inseo Jung, Jinkyu Kim +3Human-AI Interaction Persona Prompting
Korea University · Kakao Mobility · University of California, Berkeley
The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs
Apr 10, 2026Xing Zhang, Guanghui Wang, Yanwei Cui +4Language Model Safety Evaluation Personalized Language Model Alignment
AWS Generative AI Innovation Center · HSBC Holdings Plc., HSBC Technology Center, China
A Role-Based LLM Framework for Structured Information Extraction from Healthy Food Policies
Apr 2, 2026Congjing Zhang, Ruoxuan Bao, Jingyu Li +3Document Information Extraction LLM Information Extraction
Department of Industrial & Systems Engineering, University of Washington, Seattle, WA, USA · Department of Management, Shanghai University, Shanghai, China · H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA +1
Invisible Influences: Investigating Implicit Intersectional Biases through Persona Engineering in Large Language Models
Mar 16, 2026Nandini Arimanda, Achyuth Mukund, Sakthi Balan Muthiah +1Intersectional Bias in Language Models Social Bias in Language Models
Department of Computer Science and Engineering, Shiv Nadar University Chennai, Tamil Nadu, India · School of AI and CS, Plaksha University, Mohali, Punjab, India
Who Laughs with Whom? Disentangling Influential Factors in Humor Preferences across User Clusters and LLMs
Jan 6, 2026Soichiro Murakami, Hidetaka Kamigaito, Hiroya Takamura +1LLM Evaluation Human Preference Modeling
CyberAgent · Nara Institute of Science and Technology · Institute of Science Tokyo

Oct 21, 2026J/K move · Enter open · S save

A Large-Scale Evaluation of Role-Enhanced Zero-Shot Chain-of-Thought Prompting

Ibrahim Khan, Thai Van Nguyen, Yi Xia, Pratch Suntichaikul+4

College of Information Science and Technology, Ritsumeikan University, Japan · Graduate School of Information Science and Technology, Ritsumeikan University, Japan · Independent Researcher, and an alumnus of the Graduate School of Information Science and Technology, Ritsumeikan University, Japan+1

LLM Prompting Adaptive Reasoning in Language Models Language Model Reasoning Evaluation Persona Prompting

Open paper AskPDF arXiv

This paper proposes Role-Enhanced Zero-Shot Chain-of-Thought (RE-ZS-CoT), a prompting framework that systematically integrates domain-specific expert roles to enhance reasoning in large language models (LLMs) without task-specific examples. We assess two versions of our approach. In the first version, static role selection, we evaluate eight predefined expert roles across arithmetic, commonsense, and reading comprehension benchmarks to determine their impact on reasoning performance. In the second version, dynamic role selection, each model autonomously selects the single most suitable role for each benchmark, enabling adaptive task-role alignment without manual specification. Across 20 LLMs and seven benchmarks, RE-ZS-CoT frequently surpasses zero-shot and zero-shot-CoT baselines, achieving performance improvements of up to 44 percentage points. The results reveal a strong correspondence between static and dynamic versions; the benchmarks where static roles yielded improvements were almost always those where dynamic roles also outperformed baselines, though static selection achieved peak performance. Ablation studies further show that unconventional roles degrade performance, underscoring the necessity of task-role alignment. The framework's scalability is validated across model sizes (2b-14b parameters), with smaller models like Granite3.3-8b achieving remarkable proficiency in arithmetic reasoning. RE-ZS-CoT advances zero-shot prompting by unifying role specialization with chain-of-thought reasoning, offering a practical, resource-efficient solution for improving LLM capabilities across diverse domains.