DynaQuery: A Self-Adapting Framework for Querying Structured and Multimodal Data
This work addresses the problem of unreliable query generation in natural language interfaces for databases, offering a validated architectural basis for robust and adaptable systems, though it appears incremental in advancing existing paradigms.
The paper tackles the challenge of natural language querying over hybrid databases by introducing DynaQuery, a self-adapting framework that uses a Schema Introspection and Linking Engine (SILE) to nearly eliminate catastrophic failures like SCHEMA_HALLUCINATION, establishing a more robust foundation compared to unstructured retrieval methods.
The rise of Large Language Models (LLMs) has accelerated the long-standing goal of enabling natural language querying over complex, hybrid databases. Yet, this ambition exposes a dual challenge: reasoning jointly over structured, multi-relational schemas and the semantic content of linked unstructured assets. To overcome this, we present DynaQuery - a unified, self-adapting framework that serves as a practical blueprint for next-generation "Unbound Databases." At the heart of DynaQuery lies the Schema Introspection and Linking Engine (SILE), a novel systems primitive that elevates schema linking to a first-class query planning phase. We conduct a rigorous, multi-benchmark empirical evaluation of this structure-aware architecture against the prevalent unstructured Retrieval-Augmented Generation (RAG) paradigm. Our results demonstrate that the unstructured retrieval paradigm is architecturally susceptible to catastrophic contextual failures, such as SCHEMA_HALLUCINATION, leading to unreliable query generation. In contrast, our SILE-based design establishes a substantially more robust foundation, nearly eliminating this failure mode. Moreover, end-to-end validation on a complex, newly curated benchmark uncovers a key generalization principle: the transition from pure schema-awareness to holistic semantics-awareness. Taken together, our findings provide a validated architectural basis for developing natural language database interfaces that are robust, adaptable, and predictably consistent.