AI RESEARCH
QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples
arXiv CS.AI
•
ArXi:2606.04646v1 Announce Type: cross Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text. Existing retrieval-augmented generation (RAG) systems are optimized primarily for semantic relevance, but retrieving plausible passages does not guarantee correct query execution. We