New Findings: “AI on Trial: Legal Models Hallucinatein 1 Out of 6 Queries” - INFOdocket
From Stanford University Human-Centered Artificial Intelligence: Large language models have a documented tendency to “hallucinate,” or make up …
Read the original at infodocket.com ↗
- Topics
- Hallucinations & FabricationLegal & CourtsEducationChatbots & LLMs
- Mentions
- Stanford
- Tracked via
- Google Alert “AI hallucination”
Same story, other outlets
- AI on Trial: Legal Models Hallucinatein 1 out of 6 Queries - Stanford HAI Stanford HAI · May 23, 2024