Happy to announce the 2nd edition of our Summer School in Computational Social Science that will take place in the beautiful Villa del Grumello on Lake Como between June 22-26, 2026!
*** DEADLINE FOR APPLICATION: February 15, 2026 (firm deadline) ***
More details here:
css2.lakecomoschool.org
👋🏼 I'm at #EMNLP2025 presenting "The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for LLMs"
🕑 Thu. Nov 6, 12:30 - 13:30
📍 Findings Session 2, Hall C3
🚨New paper alert🚨
🤔 Ever wondered how the way you write a persona prompt affects how well an LLM simulates people?
In our #EMNLP2025 paper, we find that using interview-style persona prompts makes LLM social simulations less biased and more aligned with human opinions.
🧵1/7
Are you using survey-style questionnaires designed for humans to measure characteristics of LLMs?
In our #EACL2026 paper, we evaluate both the reliability and validity of such tests and found that their scores do not reflect real-world model behavior. In fact, they can be deceptive!
🧵1/3
📢 We are very happy to have Jana Jung for our third session of the TADA Spring Speaker Series.
Jana will present recently published work on whether psychometric tests work for LLMs.
When? 15th of April, 5pm (Berlin time)
Where? Online (Sign up for the newsletter at tada.cool)
See you there!
Francesco Pierri
🚨New paper alert🚨
🤔 Ever wondered how the way you write a persona prompt affects how well an LLM simulates people?
In our #EMNLP2025 paper, we find that using interview-style persona prompts makes LLM social simulations less biased and more aligned with human opinions.
🧵1/7
Marlene Lutz
Marlene Lutz
Jana Jung
Clint Claessen
We extensively evaluate commonly used Survey Response Generation Methods and distinguish between Token Probability-Based Methods 🟦, Restricted Generation Methods 🟧, and Open-Generation Methods 🟩…
Updated preprint: arxiv.org/abs/2510.11586
Restricted Generation Methods 🟧 lead to significant improvements in both individual-level & subpopulation-level alignment, while also being more computationally efficient than Open Generation Methods 🟩.
Alignment varies strongly between Survey Response Generation Methods, suggesting that method choice should be well-justified and documented.
Especially Token Probability-Based methods 🟦 perform poorly across all datasets…
Thrilled to share that our paper with @carohaensch.bsky.social, @barbaraplank.bsky.social & @mstrohm.bsky.social has been accepted to #ACL2026 Main!
How to generate closed-ended survey responses 📊 with LLMs trained to produce open-ended text? 📝 We show results from 32 mio. simulated responses… 🧵
Marlene Lutz
Many in-silico simulations of human survey responses with large language models (LLMs) focus on generating closed-ended survey responses, whereas LLMs are typically trained to generate open-ended text...
