arXiv AI
Verifying Text-to-SQL Queries under Changing Business Semantics
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 11
Business Truth, not SQL Accuracy: A Rule-Gated 7B Analytics Agent Outperforms a Direct-Prompted 32B Baseline
arXiv:2608. 09254v1 Announce Type: new Abstract: LLM analytics agents are evaluated on SQL syntax accuracy, but production failures look different: questions with two valid business definitions, questions the warehouse cannot answer, deprecated columns after a schema change, and queries that execute successfully while returning the wrong business number.
arXiv AI
Aug 18
Bounded Semantic Planning and Deterministic Compilation for Reliable Enterprise Text-to-SQL
arXiv:2608. 16663v1 Announce Type: cross Abstract: Direct text-to-SQL asks a language model to do two jobs: interpret the business question and construct the complete relational query.
arXiv AI
Aug 20
FinRCA-Bench: Benchmarking Evidence Retrieval and Reasoning for Financial AI Systems
FinRCA-Bench is a deterministic synthetic benchmark comprising 2,250 accounts‑payable‑to‑bank reconciliation cases that span 14 operational tables and include 1,500 injected failures across 15 causal categories. The benchmark hides root‑cause labels and record‑level evidence contracts from models, enabling independent evaluation of evidence retrieval versus reasoning accuracy. Experiments show that retrieval architecture dramatically influences performance, with retrieval improvements raising macro‑required‑record recall from 0.83% to 77.70% and exact 16‑class accuracy from 2.05% to 72.44%.
Hugging Face Trending Papers
Aug 19
FinRCA-Bench: Benchmarking Evidence Retrieval and Reasoning for Financial AI Systems
FinRCA-Bench is a synthetic benchmark designed to evaluate evidence retrieval and reasoning in financial AI systems, specifically for accounts‑payable‑to‑bank reconciliation. It contains 2,250 cases across 14 operational tables, with 1,500 injected failures in 15 causal categories and 750 hard‑negative cases, and hides root‑cause labels and evidence contracts to isolate retrieval performance. Experiments show that retrieval architecture dramatically affects accuracy, with structured retrieval methods like Typed Provenance Graph Retrieval vastly improving macro‑recall and exact‑class accuracy compared to dense semantic retrieval or classical ML.
arXiv AI
Oct 15
VeriPIE: Checkable Query Plans and Evidence-Guided Selection for Text-to-SQL
arXiv:2610.17493v1 Announce Type: cross Abstract: Financial Artificial Intelligence (AI) governance and model risk management (MRM) emphasize independent validation, transparency, and effective chall...
arXiv AI
Aug 11
Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses
arXiv:2608. 07946v1 Announce Type: cross Abstract: Text-to-SQL benchmarks ship schemas whose column names already say what the columns mean.