Not to dismiss the effort here, but wondering if this should go even further than bridging natural language to SQL. With recent work on LLMs showing promising capabilities in handling complex data structures, maybe the real play is to cut out the SQL altogether. Direct interaction with LLM-optimized data stores could yield more efficient, flexible, and fine-tuned results, eliminating the translational losses that might occur in the NL-to-SQL paradigm.
Like instead of shoehorning LLMs into old paradigms, why not conceive data storage systems inherently designed for LLM interfacing?
There's a latent inefficiency in using SQL as a bridge. It feels like trying to fit a new narrative into an old framework
And yes, rethinking database architectures from the ground up is daunting and demands more background in storage systems but given where machine learning and data interaction are heading, maybe we should consider it.
Like instead of shoehorning LLMs into old paradigms, why not conceive data storage systems inherently designed for LLM interfacing?
There's a latent inefficiency in using SQL as a bridge. It feels like trying to fit a new narrative into an old framework
And yes, rethinking database architectures from the ground up is daunting and demands more background in storage systems but given where machine learning and data interaction are heading, maybe we should consider it.