Digital Democracy and Social Cohesion

Permanent URI for this collectionhttps://hdl.handle.net/10125/112490

Browse

Recent Submissions

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item type: Item ,
    An LLM-based Multi-Agent-System for the Political Assessment of Chat-LLMs
    (2026-01-06) Johnson, Sidney; Schaal, Markus
    This paper investigates the applicability of LLM-based multi-agent systems for the political bias analysis of large language models. Following a design science research methodology, an artifact in the form of an LLM multi-agent system was created and evaluated, using the AutoGen framework. The objective was to automate and visualize bias analysis using a political questionnaire of the Bundeszentrale für politische Bildung (Federal Agency for Civic Education) in Germany. This questionnaire ("Wahl-O-Mat") contains political theses and aligns personal stances on these theses with the results of the relevant political parties in Germany. Mistral-Large-2 was chosen as an initial LLM to be evaluated with that questionnaire. The developed artifact achieved the stated goal and autonomously generated a comprehensible visualization of the results. Furthermore, the result of the automated evaluation showed a lower agreement with right-wing and right-center positions versus a higher agreement with left-wing and left-center positions.
  • Thumbnail Image
    Item type: Item ,
    Virtual Encounters, Real Impact? How Social Media Affordances Foster Intergroup Contact
    (2026-01-06) Voronin, Georg; Stieglitz, Stefan
    This paper examines how social media affordances can facilitate positive intergroup contact to enhance social cohesion in democratic societies. Using social media affordance, we analyzed 30 empirical studies published between 2012 and 2025 that investigated intergroup contact through social media platforms. Our findings reveal that 27 studies documented improved intergroup attitudes across diverse contexts spanning ethnic, religious, and sexual orientation divisions. However, the analysis exposes significant untapped potential: while some affordances dominated the research, others received little attention despite their alignment with optimal contact conditions. We demonstrate social media’s capacity to transcend traditional barriers to intergroup encounter while revealing substantial opportunities for future platform design. This implies that thoughtfully leveraged social media affordances could enable scalable interventions for strengthening inclusion principles.
  • Thumbnail Image
    Item type: Item ,
    Guardrail Vulnerabilities in Open-Source Language Models: Implications for Democratic Discourse and Marginalized Communities
    (2026-01-06) Münker, Simon; Sartori, Fabio
    The proliferation of open-source Large Language Models (LLMs) presents a complex technological phenomenon with significant societal implications. While these models democratize access to advanced Natural Language Processing (NLP) capabilities, they simultaneously amplify risks for marginalized communities who often bear the disproportionate burden of technological misuse. Our research examines systematic vulnerabilities in guardrail mechanisms across seven prominent open-source LLMs, revealing patterns of harmful content generation that threaten democratic discourse and social cohesion. Through empirical analysis using advanced NLP classification methods, we demonstrate that popular open-source models consistently generate content classified as hateful or offensive when subjected to adversarial prompting techniques. These findings directly contradict the safety assurances provided by model developers, particularly Meta AI's stated commitment that their systems should present balanced perspectives on debated policy issues rather than singular viewpoints.
  • Thumbnail Image
    Item type: Item ,
    Introduction to the Minitrack on Digital Democracy and Social Cohesion
    (2026-01-06) Fegert, Jonas; Slivko, Olga; Stieglitz, Stefan; Weinhardt, Christof