The T5-XL language model, when tuned with domain-specific instructions from the National Institute on Drug Abuse (NIDA) quiz, attempts to ask follow-up questions to gather context, whereas an ungrounded ChatGPT model may produce unsafe responses.

Authors

• Person: Not available Organization: arXiv
  Building Trustworthy NeuroSymbolic AI Systems - arXiv

Sources

• Building Trustworthy NeuroSymbolic AI Systems - arXiv arxiv.org arXiv via serper

Referenced by nodes (2)

• ChatGPT concept
• AI safety and security concept