# BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra Source: [BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:52:14.378Z Authors: Parker Glenn, Parag Pravin Dakle, Liang Wang, Preethi Raghavan Published: 2024-02-27T20:48:24.000Z ## Abstract Many existing end-to-end systems for hybrid question answering tasks can often be boiled down to a "prompt-and-pray" paradigm, where the user has limited control and insight into the intermediate reasoning steps used to achieve the final result. Additionally, due to the context size limitation of many transformer-based LLMs, it is often not reasonable to expect that the full structured and unstructured context will fit into a given prompt in a zero-shot setting, let alone a few-shot setting. We introduce BlendSQL, a superset of SQLite to act as a unified dialect for orchestrating reasoning across both unstructured and structured data. For hybrid question answering tasks involving multi-hop reasoning, we encode the full decomposed reasoning roadmap into a single interpretable BlendSQL query. Notably, we show that BlendSQL can scale to massive datasets and improve the performance of end-to-end systems while using 35% fewer tokens. Our code is available and installable as a package at https://github.com/parkervg/blendsql. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Tabular Reasoning on Tabular Reasoning](): Tabular Reasoning; Tabular Reasoning; F1 Score: 11.56. ## Original sources and implementation [Original paper]() [PDF]()