Dear WHAT-IF members and interested colleagues,

We’re six months into the project and our team members have made significant progress across their respective work packages. Over the summer, WHAT-IF researchers have been developing their data collection methods, forming new partnerships, and presenting conceptual work at academic conferences, sharing early insights with the broader academic community:

New strategic partnership with real-world practitioners to advance misinformation research

In a recent blog post, we describe our partnership with Spanish media literacy and fact-checking organizations Learn to Check! and maldita.es. As part of the data collection in Spain, Learn to Check! is developing visual graphics, videos, and textual resources to help people spot misinformation. Maldita is contributing verified fact-checks from their daily work. The goal? Creating evidence-based solutions on when and how citizens become better equipped to navigate the media ecosystem, while maintaining scientific rigor!

At the Social Simulation Conference

At the Social Simulation Conference 2025 in Delft (25-29 August), Aytalina Kulichkina presented the ongoing WHAT-IF project and its conceptual model. She shared the preliminary design components and gathered valuable feedback from the social simulation community. The conference’s theme, “Social simulation in a socio-technical context: embracing societies’ complexities,” provided a vibrant setting for debates on the integration of Large Language Models (LLMs) with Agent-Based Models (ABMs).

Among the highlights were discussions on when an LLM-augmented ABM can add value, trade-offs between behavioral nuance and computational tractability, and potential use cases: from emergent narrative generation to scenario simulation. These insights and exchanges will support the further development of the project.

Large Language Models workshop

Taehee Kim presented research on replicating LLM-fired agents (title: “Evaluating Generative Agents in Social Media: Replicating User Attitudes and Behaviors”) at the EPSA LLM Workshop on June 25th, 2025 in Madrid, Spain. The workshop brought together scholars working with Large Language Models in social science applications, covering topics from AI agents in experiments to data analysis, design guidance, and the ethical challenges of incorporating LLMs into research.

Again: please share!

Please forward this newsletter to your team members or colleagues interested in our project.

The newsletter serves as a platform to share updates on our research presentations, announce upcoming events and publications, and keep everyone connected with our latest work. We’ll continue sending these updates to subscribers and publishing them on our website every three months.