Refusals and Caveats

Cross-source consensus on Refusals and Caveats from 1 sources and 5 claims.

1 sources · 5 claims

How it works

Only two of the 250 responses were refusals, and both came from Meta AI. — Generative artificial intelligence-driven chatbots and medical misinformation: an accuracy, referencing and readability audit
Caveats and disclaimers were unevenly distributed across chatbot responses. — Generative artificial intelligence-driven chatbots and medical misinformation: an accuracy, referencing and readability audit
Refusal can be the most ethical response when prompts request contraindicated medical advice. — Generative artificial intelligence-driven chatbots and medical misinformation: an accuracy, referencing and readability audit
Gemini included caveats more often than expected, while ChatGPT included fewer than expected. — Generative artificial intelligence-driven chatbots and medical misinformation: an accuracy, referencing and readability audit
Models designed to avoid evasiveness may choose to answer unsafe requests instead of declining them. — Generative artificial intelligence-driven chatbots and medical misinformation: an accuracy, referencing and readability audit