Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
General Text-to-SQL systems struggle with production financial databases due to opaque integer IDs and complex schemas, failing to achieve 50% accuracy. Financial LINking Text-to-SQL (FLINT) addresses this by employing a lookup agent for concept-to-constraint resolution, embedding-based retrieval of query templates, and foreign-key-based schema pruning. FLINT achieves state-of-the-art performance on production financial data and is deployed in a real-world financial data retrieval service.
Opaque IDs and complex joins cripple general Text-to-SQL in finance; FLINT bridges the gap, achieving production-ready accuracy.
General-purpose Text-to-SQL systems achieve strong performance on academic benchmarks like Spider and BIRD, where schemas are relatively shallow and column values are often human readable. In production financial databases, where concepts are stored as opaque integer keys rather than human-readable strings, these methods fall below 50%, as even simple queries require multiple joins and filter predicates reference opaque IDs. We present Financial LINking Text-to-SQL (FLINT), a domain-specialized Text-to-SQL system that closes this gap through three key components: (1) a lookup agent that dynamically resolves natural-language concepts to question-specific reference table constraints, (2) embedding-based retrieval of structurally similar query templates from a compact, expert-authored bank, and (3) schema linking that prunes a large table schema to the relevant subset by traversing foreign-key chains, rather than relying on name similarity alone. We evaluate on two datasets totaling 359 questions over production financial schemas. FLINT outperforms various state-of-the-art baselines using the same LLM. The system is deployed in production as part of a financial data retrieval service.