{
  "id": 1990,
  "url": "https://link.springer.com/article/10.1007/s10462-026-11548-z",
  "title": "A systematic review of toxicity in large language models: definitions, datasets, detectors, detoxification methods and challenges",
  "summary": "The emergence of the transformer architecture has ushered in a new era of possibilities, showcasing remarkable capabilities in generative tasks exemplified by models like GPT4o, Claude 3, and Llama 3. However, these advancements come with a caveat: predominantly trained on data gleaned from social media platforms, these systems inadvertently perpetuate societal biases and toxicity. Recognizing the paramount importance of AI Safety and Alignment, our study embarks on a thorough exploration throug",
  "authors": null,
  "category": "research",
  "topics": "safety-alignment",
  "orgs": "anthropic,meta",
  "regions": null,
  "published_at": "2026-07-02T00:00:00.000Z",
  "fetched_at": "2026-07-14T16:11:46.979Z",
  "source_slug": "x-artificial-intelligence-review",
  "source_name": "Artificial Intelligence Review",
  "source_homepage": "https://link.springer.com/journal/10462",
  "ethics_ai_record_url": "https://ethics.ai/record/1990",
  "original_url": "https://link.springer.com/article/10.1007/s10462-026-11548-z",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}