Safety metrics for critical AI applications must be rooted in domain expertise and align with the expectations of domain experts, rather than relying solely on open-domain metrics used for LLMs.

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)

• Large Language Models concept
• artificial intelligence concept