Incorporating clinically validated knowledge into LLMs enhances user-level explainability by allowing the model to base decisions on clinical concepts that are comprehensible and actionable for clinicians, potentially enabling the LLM to follow a clinician’s decision-making process through NeuroSymbolic AI, as proposed by Sheth, Roy, and Gaur (2023).

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
• Neuro-symbolic artificial intelligence concept