Research

Paper

AI LLM March 02, 2026

Ignore All Previous Instructions: Jailbreaking as a de-escalatory peace building practise to resist LLM social media bots

Authors

Huw Day, Adrianna Jezierska, Jessica Woodgate

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.

Metadata

arXiv ID: 2603.01942
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-03-02
Fetched: 2026-03-03 04:34

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.01942v1</id>\n    <title>Ignore All Previous Instructions: Jailbreaking as a de-escalatory peace building practise to resist LLM social media bots</title>\n    <updated>2026-03-02T14:57:13Z</updated>\n    <link href='https://arxiv.org/abs/2603.01942v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.01942v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-02T14:57:13Z</published>\n    <arxiv:comment>Accepted to ICLR 2026 AI for peace workshop</arxiv:comment>\n    <arxiv:primary_category term='cs.HC'/>\n    <author>\n      <name>Huw Day</name>\n    </author>\n    <author>\n      <name>Adrianna Jezierska</name>\n    </author>\n    <author>\n      <name>Jessica Woodgate</name>\n    </author>\n  </entry>"
}