Ignore All Previous Instructions: Jailbreaking as a de-escalatory peace building practise to resist LLM social media bots
On the map: LLM safety and security → Jailbreaking
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 11 of its 37 references that are in the map. First posted on arXiv 2 Mar 2026.
Builds on
11 of 37 references.
Closest ancestors · 3
Same direction, newest first
- 2025Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models19 Nov
- 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul
- 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study23 May
Other references · 8
- 2023A Comprehensive Overview of Large Language Modelscited by 648
- 2014The Rise of Social Botscited by 96
- 2022Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methodscited by 79
- 2024Escalation Risks from Language Models in Military and Diplomatic Decision-Makingcited by 63
- 2023Disinformation Detection: An Evolving Challenge in the Age of LLMscited by 41
- 2023Disinformation Capabilities of Large Language Modelscited by 25
- 2023LLM generated responses to mitigate the impact of hate speechcited by 7
- 2016On Profiling Bots in Social Mediacited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models
- 2023Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks
- 2025Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is
- 2025Uncovering the Persuasive Fingerprint of LLMs in Jailbreaking Attacks
- 2024Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks
- 2024Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models
- 2025Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking
- 2026How Far Will They Go? Red-Teaming Online Influence with Large Language Models