paperSeptember 2026Unreviewed

Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking

Siyu Chen, Haoran Wang, Xiaojian Li, Yao Huang, Yinpeng Dong, Wei Xu

Abstract

Multi-turn jailbreak attacks demonstrate that harmful intent can be distributed across dialogue, yet existing methods obscure what conversational mechanisms drive vulnerability. We introduce BLUEPRINT, a safety-evaluation framework separating a factorized social-influence strategy space from WORLDVIEWSIM, a cross-turn situational context module. Monte Carlo Tree Search optimizes turn-level combinations of 18 theory-grounded influence factors across a four-turn trajectory. Across six frontier mod

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@misc{chen2026before,
  title = {{Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking}},
  author = {Siyu Chen and Haoran Wang and Xiaojian Li and Yao Huang and Yinpeng Dong and Wei Xu},
  year = {2026},
  month = sep,
  eprint = {2609.02414},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.02414}
}