{
  "id": 9190,
  "url": "https://doi.org/10.18653/v1/2022.emnlp-main.225",
  "title": "Red Teaming Language Models with Language Models",
  "summary": "Ethan Perez, Saffron Huang, Francis Song, Trevor Cai, Roman Ring, John Aslanides, Amelia Glaese, Nat McAleese, Geoffrey Irving. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.",
  "authors": "Ethan Perez, Saffron Huang, Francis Song, Trevor Cai, Roman Ring, John Aslanides",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2022-01-01T00:00:00.000Z",
  "fetched_at": "2026-07-14T16:33:50.749Z",
  "source_slug": "openalex",
  "source_name": "OpenAlex",
  "source_homepage": "https://openalex.org",
  "ethics_ai_record_url": "https://ethics.ai/record/9190",
  "original_url": "https://doi.org/10.18653/v1/2022.emnlp-main.225",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}