Grounded rules in AI models provide two safety benefits: they tend to be helpful and harmless, and they promote absolute learning by avoiding tricky trade-off situations.

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 (1)

• AI models concept