{
  "id": 4550,
  "url": "https://arxiv.org/abs/2605.10633v1",
  "title": "Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs",
  "summary": "Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work links these failures to specific directions in the activation space, their relationship to the model's broader persona remains unexplored. We map the latent personality space of LLMs through established psychometric profiles like the Big Five, Dark Triad, and LLM-specific behaviors (e.g. evil, sycophancy), and show that t",
  "authors": "Krishak Aneja, Manas Mittal, Anmol Goel, Ponnurangam Kumaraguru, Vamshi Krishna Bonagiri",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-11T14:21:57.000Z",
  "fetched_at": "2026-07-14T16:31:03.581Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4550",
  "original_url": "https://arxiv.org/abs/2605.10633v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}