mlsanityData to 13 Oct 2026

DynaQuery: A Self-Adapting Framework for Querying Structured and Multimodal Data

arXiv 2510.18029 ↗First posted 20 Oct 2025cs.DB cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 20 of its 43 references that are in the map. First posted on arXiv 20 Oct 2025.

Builds on

20 of 43 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2020Language Models are Few-Shot Learnerscited by 32,320
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,221
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,156
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,133
  6. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 680
  7. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 562
  8. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 472
  9. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 383
  10. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 229
  11. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  12. 2024A Theoretical Understanding of Self-Correction through In-context Alignmentcited by 44
8 more
  1. 2023Evaluating Cross-Domain Text-to-SQL Models and Benchmarkscited by 32
  2. 2024Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrievalcited by 27
  3. 2023CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQLcited by 23
  4. 2024Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translationcited by 21
  5. 2022N-Best Hypotheses Reranking for Text-To-SQL Systemscited by 19
  6. 2021An Investigation Between Schema Linking and Text-to-SQL Performancecited by 5
  7. 2025RAISE: Reasoning Agent for Interactive SQL Explorationcited by 4
  8. 2025RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQLcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SemBench: A Benchmark for Semantic Query Processing Engines
  2. 2025Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB
  3. 2024Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data
  4. 2025Weaver: Interweaving SQL and LLM for Table Reasoning
  5. 2026SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction
  6. 2025Simplifying Data Integration: SLM-Driven Systems for Unified Semantic Queries Across Heterogeneous Databases
  7. 2024From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems
  8. 2026DynaRAG: Bridging Static and Dynamic Knowledge in Retrieval-Augmented Generation