Ignore All Previous Instructions: Jailbreaking as a de-escalatory peace building practise to resist LLM social media bots
Abstract
Large Language Models have intensified the scale and strategic manipulation of political discourse on social media, leading to conflict escalation. The existing literature largely focuses on platform-led moderation as a countermeasure. In this paper, we propose a user-centric view of "jailbreaking" as an emergent, non-violent de-escalation practice. Online users engage with suspected LLM-powered accounts to circumvent large language model safeguards, exposing automated behaviour and disrupting the circulation of misleading narratives.
Fields of Study & Subjects
Misinformation and Its Impacts
Ethics and Social Impacts of AI
Social Media and Politics
Publication details
- Journal / source
- arXiv (Cornell University)
- Publication date
- 2 March 2026
- Language
- EN
- Document type
- Preprint