paper-with-me

홈 › Papers

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

2025-10-20 · Aymane Hassini 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.

📄 PDF Abstract BibTeX arXiv:2510.18029

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Querying Databases with Function Calling

2025-01-23 · Connor Shorten, Charles Pierse, Thomas Benjamin Smith, Karel D'Oosterlinck 외

The capabilities of Large Language Models (LLMs) are rapidly accelerating largely thanks to their integration with external tools. Querying databases is among the most effective of these integrations, enabling LLMs to ac…

Harnessing Large Language Models for Precision Querying and Retrieval-Augmented Knowledge Extraction in Clinical Data Science

2026-01-28 · Juan Jose Rubio Jan, Jack Wu, Julia Ive arxiv

This study applies Large Language Models (LLMs) to two foundational Electronic Health Record (EHR) data science tasks: structured data querying (using programmatic languages, Python/Pandas) and information extraction fro…

Information ExtractionSemantic Similarity

Decoding AI Judgment: How LLMs Assess News Credibility and Bias

2025-02-06 · Edoardo Loru, Jacopo Nudo, Niccolò Di Marco, Matteo Cinelli 외

Large Language Models (LLMs) are increasingly used to assess news credibility, yet little is known about how they make these judgments. While prior research has examined political bias in LLM outputs or their potential f…

Fact Checking

API-Assisted Code Generation for Question Answering on Varied Table Structures

2023-10-23 · Yihan Cao, Shuyi Chen, Ryan Liu, Zhiruo Wang 외

A persistent challenge to table question answering (TableQA) by generating executable programs has been adapting to varied table structures, typically requiring domain-specific logical forms. In response, this paper intr…

Code GenerationQuestion Answering

Future Querying: Can LLMs Serve as Implicit Medical World Models?

2026-08-24 · Siri Willems, James Butterworth, Lore Goetschalckx, Peter Vrancx 외 arxiv

Traditional clinical prediction models rely on task-specific pipelines and curated, structured data, which scale poorly and underutilize unstructured text. To address this, we introduce future querying, a paradigm that p…

Feature Engineering