Assessing the Reliability of Persona-Conditioned LLMs as Synthetic Survey Respondents
Top Cited Papers
Open Access
- 28 May 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 320-329
Abstract
No abstract availableAll Related Versions
Funding Information
- European Union - Next Generation EU (101113826)
- European Union - Next Generation EU (PE00000013)
- European Union - Next Generation EU (B53D23013290006)
- Italian Ministry of Education and Research (FoReLab)
This publication has 10 references indexed in Scilit:
- Evaluating the Simulation of Human Personality-Driven Susceptibility to Misinformation with LLMs2025
- Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and TargetsProceedings of the International AAAI Conference on Web and Social Media, 2025
- Evaluation of Reliability Criteria for News Publishers with Large Language Models2025
- SimSpark: Interactive Simulation of Social Media BehaviorsProceedings of the ACM on Human-Computer Interaction, 2025
- Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language ModelsProceedings of the AAAI Conference on Artificial Intelligence, 2025
- Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?2025
- Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations2025
- Investigating Cultural Alignment of Large Language Models2024
- PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits2024
- CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations2023