Event

Research on Open Source LLM Safety at HICSS 2026

From January 6-9, 2026, TWON researcher Simon Münker presented his paper at the Hawaii International Conference on System Sciences (HICSS), one of the leading international conferences in the field of information systems and digital innovation.

The paper addresses societal risks associated with open source Large Language Models and evaluates the effectiveness of existing safety and guardrail mechanisms. Together with his co author Fabio Sartori, Simon Münker received the Best Paper Award for this research.

The study systematically examines guardrail vulnerabilities across seven widely used open source LLMs. Using advanced natural language processing classification methods, it identifies recurring patterns of harmful content generation under adversarial prompting. These vulnerabilities were first observed during earlier research activities within the TWON project, where initial experiments revealed persistent weaknesses in model safety mechanisms.

The findings show that several prominent models consistently produce content classified as hateful or offensive. This raises concerns about the potential implications of open source LLMs for democratic discourse and social cohesion. In particular, the results challenge public safety assurances by model developers and point to discrepancies between stated safeguards and observed model behavior.

The research contributes to ongoing discussions on responsible AI development and the governance of AI systems that shape online communication and public discourse. It underlines the need for more robust, transparent and empirically tested safety mechanisms in open source AI ecosystems.

The paper was presented as part of the Digital Democracy Minitrack at HICSS 2026.

Rethinking AI for Democratic Societies – Joint Event in Ljubljana, October 14

On October 14, partners from the projects AI4Gov, SOLARIS, and TWON gathered in Ljubljana to explore how artificial intelligence can support democracy, transparency, and citizen participation.

The event titled AI, Democracy and the Public Interest: Building Resilient Digital Futures brought together experts from research, policy, civil society, and industry. The program included project presentations, followed by a panel discussion featuring contributors such as Federica Russo and Tanja Zdolsek Draksler.

Hosted at Hotel City Ljubljana, the event “AI, Democracy, and the Public Interest: Building Resilient Digital Futures” brought together experts from research, policy, civil society, and industry. The program included project presentations, followed by a panel discussion featuring contributors such as Federica Russo and Tanja Zdolšek Draksler.

Our researcher Alenka Guček introduced TWON in an expert talk, while Achim Rettinger participated as a panelist in a discussion on the influence of AI technologies on democratic processes and public trust.

The event concluded with networking and informal exchanges on how to build ethical, democratic, and human-centered digital futures.

Discussions throughout the day highlighted the need for greater transparency and accountability in AI systems, stronger cooperation across sectors, and increased public understanding of AI’s societal impact. The full recordings are now available online.

As TWON, we emphasize the importance of strengthening connections between European research and policy efforts on AI and democracy. Our sincere thanks go to the Solaris and AI4Gov teams for making this event possible.