The authors propose the CREST framework for achieving trustworthiness in Large Language Models, which stands for Consistency, Reliability, user-level Explainability, and Safety.

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 (5)

• Large Language Models concept
• reliability concept
• safety concept
• consistency concept
• CREST framework concept