{"slug": "fraudbench-a-legal-evaluation-of-ai-deception", "title": "FraudBench: A Legal Evaluation of AI Deception", "summary": "A new evaluation called FraudBench has been introduced to measure large language models' propensity to recommend, assist, or directly take actions that would constitute fraud under U.S. law. FraudBench uses a novel dataset of 159 scenarios drawn from real-world U.S. court cases and validated by legal experts. The benchmark matters because it gives developers a legally grounded way to test whether LLMs will aid fraudulent conduct.", "body_md": "We introduce FraudBench, an evaluation of large language models' (LLMs) propensities to recommend, assist, or directly take actions that would constitute fraud under U.S. law. Our evaluation contains a novel dataset of 159 scenarios based on real-world U.S. court cases and validated by legal experts", "url": "https://wpnews.pro/news/fraudbench-a-legal-evaluation-of-ai-deception", "canonical_source": "https://aiflash.com/news/149458/", "published_at": "2026-11-10 20:30:14+00:00", "updated_at": "2026-11-10 20:53:51.971349+00:00", "lang": "en", "topics": ["ai-safety", "large-language-models", "ai-ethics", "ai-research"], "entities": ["FraudBench"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/fraudbench-a-legal-evaluation-of-ai-deception", "markdown": "https://wpnews.pro/news/fraudbench-a-legal-evaluation-of-ai-deception.md", "text": "https://wpnews.pro/news/fraudbench-a-legal-evaluation-of-ai-deception.txt", "jsonld": "https://wpnews.pro/news/fraudbench-a-legal-evaluation-of-ai-deception.jsonld"}}