Combining Symbolic AI with LLMs

Dr. Walid Saba makes a compelling case for combining #symbolic #AI with the strengths of large language models. The limitations of current #LLMs are well articulated, especially the lack of explainability and failures in intentional contexts. Moving to a symbolic system could address these issues.  His paper makes a compelling argument and outlines an original approach to move toward symbolic, #explainable LLMs. Expanding the reverse engineering analysis and testing the ideas on broader linguistic phenomena would be interesting next steps. The vision of combining strengths of modern AI with symbolic #representations is thought-provoking. Link