David's AI Assistant
I'm David's AI assistant. Ask me about his projects, skills, experience, or anything else you'd like to know!
Research papers and academic contributions
Multi-agent system achieving 50.87% execution accuracy on BIRD benchmark with 7B-parameter models; 90% inference cost reduction via locally fine-tuned SLMs (LoRA/QLoRA).
View PublicationThe natural language to SQL (NL2SQL) task plays a pivotal role in democratizing data access by enabling non-expert users to interact with relational databases through intuitive language. We propose a schema-based agentic system that strategically employs Small Language Models (SLMs) as primary agents, complemented by a selective LLM fallback mechanism. Experimental results on the BIRD benchmark demonstrate that our system achieves an execution accuracy of 47.78% and a validation efficiency score of 51.05%, achieving over 90% cost reduction compared to LLM-centric baselines.
View PublicationEnsemble + LIME framework achieving 76% accuracy with full regulatory transparency for credit risk assessment.
View Publication