TL;DR
This study provides an initial assessment on the feasibility of using LLMs as a KB for CH, using “Galois”, a recent framework for executing Structured Query Language (SQL) queries over LLMs with logical and physical optimizations tailored to the model’s behavior.
Querying LLMs as digital libraries is feasible, but its effectiveness depends on model strength, deployment conditions, dataset structure, and execution strategy, and Galois remains valuable when relational discipline and controlled query execution are required.
How users actually use LLM-powered data systems is examined: how they struggle to specify and validate queries, how they iterate extensively to converge on bespoke operators specific to their documents and domains, and what these patterns imply for the systems and benchmarks their community should be building.
An agentic framework that leverages Large Language Models (LLMs) for generating UDF-centric queries from natural language task descriptions in the medical domain is presented, demonstrating that structured tool orchestration with verification loops substantially improves generation quality.
Query2Property is presented, a semantic retrieval system that maps natural language queries to the most relevant IFC properties by embedding both property descriptions and user queries in a shared vector space, supporting semantic search and natural language exploration of complex building information.
This paper introduces ExplAIner, a query language based on FOIL with an extended vocabulary and a layered structure that can express a broad family of explanation notions, and proves that the evaluation problem for each query in ExplAIner belongs to the Boolean hierarchy over every class of Boolean models for which som...
This work recast five text-to-SQL datasets as retrieval tasks at both table and column granularity, covering realistic and enterprise-scale schemas under two document representations, and proposes corpus-adaptive fine-tuning, establishing schema linking as a standalone retrieval task and lightweight, label-free corpus...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
