Sleeper agents: Training deceptive LLMs that persist through safety training

{
  "doi": null,
  "year": 2024,
  "title": "Sleeper agents: Training deceptive LLMs that persist through safety training",
  "venue": null,
  "authors": [
    "Hubinger, E.",
    "Denison, C.",
    "Mu, J.",
    "Lambert, M.",
    "Tong, M.",
    "MacDiarmid, M.",
    "Lanham, T.",
    "Ziegler, D. M.",
    "Maxwell, T.",
    "Cheng, N."
  ],
  "arxiv_id": "2401.05566",
  "s2_paper_id": null,
  "ingest_status": "referenced-only"
}