Similar papers
ExpeSQL: An Efficient, Experience-Guided Decompositional Search Framework for Text-to-SQL
This work introduces ExpeSQL, a zero-shot, open-source–compatible, and efficient framework that combines divide-and-conquer reasoning, Best-of-N candidate selection, and self-critique with experience-guided refinement that establishes a new paradigm for deployable, self-improving Text-to-SQL systems in dynamic, real-wo...
Unknown authors
· 0 citations
Conference
Aug 2026
"Question→SQL→Wiki" Dynamic Wiki Graph for NL2SQL
To bridge the semantic gap in NL2SQL (Natural Language to SQL) tasks, this study proposes a "Question→SQL→Wiki" framework that leverages a dynamic Wiki Graph as an intermediate reasoning layer. Departing from conventional NL2SQL approaches that rely solely on end-to-end mapping, our method utilizes Large Language Model...
Jia-Xuan Liu, Shi-Yu Fang, Ji-Bing Wu et al.
· 2026 12th International Conf... · 0 citations
Aug 2026
Text-to-SQL Evaluation Toolkit
Text-to-SQL systems translate natural language questions into executable SQL queries, enabling intuitive access to structured data. While recent large language models have substantially improved generation quality, evaluating these systems remains a complex challenge: SQL semantics are subtle, multiple valid query form...
Oktie Hassanzadeh, Yotam Perlitz, Nhan H. Pham et al.
· Proceedings of the VLDB Endo... · 0 citations
BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations
BIRD-History is introduced, a benchmark consisting of 1,393 tasks across 11 databases, designed to evaluate text-to-SQL systems'ability to ground underspecified natural language questions using historical SQL scripts, and a plug-in retriever that extracts five types of external knowledge from historical SQL scripts, th...
Yun-Fan Zhou, Qi-Ming Shi, Yi-Zhou Yang et al.
· 0 citations
Preprint
Aug 2026
Guided Table Retrieval for Structured Data Search
guided table retrieval is presented, a four-phase pipeline that combines deterministic grounding via hash-based predictors, structural exploration of join-graph reachability, LLM-powered disambiguation of sources and targets, and algorithmic merging into minimal, topologically ordered join trees.
Alekh Jindal, J. Pandey, C. Pavlopoulou et al.
· 0 citations
A Cost-Aware Agentic Architecture for NL-to-SQL over Nested Enterprise Schemas, with a New Benchmark
Natural-language-to-SQL systems have ad- vanced rapidly on academic benchmarks, yet production enterprise schemas exhibit graph- like, semi-structured, deeply nested structure that current benchmarks do not measure. We make two complementary contributions. First, we introduce the DevRev NL2SQL bench- mark: 900 executio...
Yoga Sri Varshan Varadharajan, Ajay Yadav, Ritesh Goru et al.
· 0 citations