HCMar 2
Ignore All Previous Instructions: Jailbreaking as a de-escalatory peace building practise to resist LLM social media botsHuw Day, Adrianna Jezierska, Jessica Woodgate
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.