Agenda

Taking Sides, Telling Stories: LLMs in the Analysis of Public Discourse | July 7 - 8, 2025

The workshop focuses on the dual role that large language models (LLMs) play in analyzing public discourse: identifying positions and opinions, and reconstructing narratives and meaning. We offer a critical reflection on their impact within contemporary social and communicative contexts by exploring the potential and limitations of LLMs in understanding, annotating, and generating complex discursive content. We explore the focus on the dynamics of conflict and cooperation both within LLMs and using alternative experimental tools that may complement the understanding of the evolution of cooperation.

The workshop is held in hybrid mode:

• Sign up here to participate in person
• Sign up here to participate online

Programme, July 7

14 – 14.30  -  Registration and welcome coffee

14.30 – 14.45 - Welcome and agenda for the workshop

14.45 – 16.15 - Keynote session with Andrea Baronchelli
Emergent social conventions and collective bias in LLM populations
Social conventions are the foundation of social coordination, shaping how individuals form a society. In this talk, I will present theoretical and experimental findings that demonstrate the spontaneous emergence of social norms in human groups, as well as the existence of tipping points in social convention. I will then explore the case of populations of large language models (LLMs). As AI agents increasingly communicate using natural language, understanding how they develop conventions is crucial for interpreting and managing their collective behaviour. I will show that LLM populations can establish social conventions and highlight how collective biases can emerge even when individual agents appear unbiased. The ability of AI agents to develop norms without explicit programming has significant implications for designing AI systems that align with human values and societal goals.

Andrea Baronchelli is Professor of Complexity Science at City, St George’s University London. His research focuses on human dynamics in decentralised socio-technical systems, covering topics such as social norms, (mis)information spreading, polarisation in social networks, blockchain ecosystems, and dark markets. Andrea’s work has been published in high-impact journals including Nature, Science, PNAS, and Nature Human Behaviour, and has been widely covered in the press, informing public debate and helping shape policy. In 2019, he received the Young Scientist Award for Socio- and Econophysics from the German Physical Society (DPG). From 2019 to 2021, he led the Economic Data Science theme at The Alan Turing Institute, where he launched the Token Economy theme in 2021 and led it until 2025.

16.15 – 18 Session 1:  Annotating Opinions and Unfolding Stories: LLMs for Stance Detection and Narrative Analysis
Veronika Batzdorfer - Synthetic Annotators for Sensitive Narratives: LLMs in Psychological Text Analysis and Bias Detection.
Jimena Royo Letelier - LLM based annotations at scale.
General discussion

18 – 19 Networking cocktail

The event is organized in the framework of Project “SoMe4Dem.Social media for democracy – understanding the causal mechanisms of digital citizenship”, financed by the European Union’s Horizon Europe Programme under Grant Agreement No. 101094752 – CUP H73C22001540006