arXiv:2608.29345v1 Announce Type: new Abstract: While recent Large Language Model (LLM)-based text-to-SQL systems achieve impressive performance on standard benchmarks, they struggle when user querie...
Retrieval in the SQL setting has largely been studied as the task of finding, within a large collection of SQL statements, the statement that answers a natural-language question. At scale, however, a more fundamental retrieval problem precedes generation: schema retrieval, identifying the tables and columns a question requires in a database that may contain thousands of them, far more than fit in a model's context.
The paper introduces FLINT, a domain‑specialized Text‑to‑SQL system designed for complex financial databases where data is stored as opaque integer keys. FLINT employs a lookup agent to resolve natural‑language concepts, uses embedding‑based retrieval of query templates from a compact expert‑authored bank, and prunes large schemas by traversing foreign‑key chains. Evaluated on 359 questions across two production financial schemas, FLINT outperforms state‑of‑the‑art baselines and is already deployed in a financial data retrieval service.
Reflect‑SQL is a new framework for converting natural language into SQL queries. It tackles challenges such as large, obscure database schemas, poor table and column retrieval, and syntactically or logically flawed SQL by using a multi‑stage self‑reflection approach. The system iteratively refines queries and SQL through feedback loops driven by an LLM‑as‑a‑judge, achieving 72.03% execution accuracy on the BIRD benchmark, outperforming existing baselines.
arXiv:2606. 28387v1 Announce Type: cross Abstract: Enterprise text-to-SQL systems often fail before SQL is generated: the model receives the wrong schema context.
arXiv:2606. 28601v1 Announce Type: cross Abstract: Recent progress in Text-to-SQL has been driven by stronger language models and prompting strategies, yet performance on real enterprise benchmarks such as Spider 2.
arXiv:2607. 18029v1 Announce Type: cross Abstract: Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured queries on the metadata.
The paper investigates whether a knowledge graph can enhance retrieval for enterprise retrieval‑augmented generation (RAG) systems compared to traditional similarity search. Using a snapshot of SEC EDGAR filings, the authors built a graph with 430,257 nodes and 561,144 edges, then evaluated three architectures—text‑to‑SQL, dense‑vector RAG, and a two‑stage GraphRAG. GraphRAG outperformed the other methods, correctly answering 16 of 20 questions across all attempts, while the other approaches lagged behind, especially in structured aggregation and single‑document queries.
The paper introduces EXYGEN, a framework that enables conversational access to large knowledge graphs by combining VoID descriptions, ShEx schemas, retrieved triples, and example question‑query pairs in a retrieval‑augmented generation pipeline. On the SciQA benchmark, this approach achieves an exact‑match score of 0.419 without fine‑tuning any large language model, and shows that larger general‑purpose LLMs can outperform smaller code‑specialized ones when provided sufficient context. To scale metadata generation for very large KGs, the authors propose a predicate‑coverage‑aware parallel graph sampling strategy that preserves structural diversity, reduces runtime by over 80× on OpenCitations Meta and GESIS, and is the only tractable method for obtaining complete metadata on ORKG.
arXiv:2609.14652v1 Announce Type: cross Abstract: Large Language Model (LLM) applications often transfer domain concepts into the model's context informally, through prompt prose, schema dumps, and e...
arXiv:2610.03625v1 Announce Type: cross Abstract: Relational databases are among the most widely deployed forms of structured knowledge, and natural language access to them requires grounding languag...
Build2SPARQL is a large-scale benchmark dataset for translating natural-language questions into SPARQL queries over building knowledge graphs. The dataset is generated by a KG‑grounded pipeline that produces 6,136 executable SPARQL queries and 30,680 corresponding natural-language questions across six query-pattern families and five vocabulary registers, covering 201 building KGs. Human validation shows high semantic fidelity, naturalness, and operational plausibility, and retrieval‑augmented evaluation demonstrates significant accuracy gains for open‑weight language models.