{
  "id": 1427,
  "url": "https://arxiv.org/abs/2606.06099v1",
  "title": "CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Model",
  "summary": "Whether Large Language Models (LLMs) exhibit covert psychological manipulation in complex human-AI interactions has garnered increasing safety concerns. However, existing AI safety benchmarks remain largely restricted to explicit rule compliance and static prompts, failing to capture the dynamic and covert nature of manipulative strategies in multi-turn dialogues. We introduce CogManip, a comprehensive benchmark that evaluates 15 manipulation strategy risks across 1,000 multi-turn interaction sc",
  "authors": "Zeyang Yue, Chenfei Yan, Feifei Zhao, Haibo Tong, Mengwen Xu, Xiaozhen Wang et al.",
  "category": "research",
  "topics": "regulation,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-04T12:38:43.000Z",
  "fetched_at": "2026-07-14T14:15:17.100Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1427",
  "original_url": "https://arxiv.org/abs/2606.06099v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}