Coalesce 2024: What does enterprise AI lose by not investing in semantics and knowledge?
In this talk, we will make the case that the success of enterprise AI depends on an investment in semantics and knowledge, not just data.
In this talk, we will make the case that the success of enterprise AI depends on an investment in semantics and knowledge, not just data. Our LLM Accuracy benchmark research provided evidence that by layering semantic layers/knowledge graphs on enterprise SQL databases increases the accuracy of LLMs at least 4X for question answering. This work has been reproduced and validated by many others, including dbt labs. It's fantastic that semantics and knowledge are getting the attention it deserves. We need more. This talk is targeted to 1) those who believe AI accuracy can be improved by simply adding more data to fine-tune/train models, and 2) the believers in semantics and knowledge who need help getting executive buy-in. We will dive into:
- the knowledge engineering work that needs to be done
- who should be leading this work (hint: analytics engineers)
- what companies lose by not doing this knowledge engineering work
Speaker: Juan Sequeda, Principal Scientist and Head of AI Lab @ data.world