# BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra

arXiv: https://arxiv.org/abs/2402.17882 · HTML: https://mlsanity.com/paper/2402.17882/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 26 of 26)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning](https://mlsanity.com/paper/2105.04165/) (2021)
- [Large Language Models as Tool Makers](https://mlsanity.com/paper/2305.17126/) (2023)
- [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs](https://mlsanity.com/paper/2303.16434/) (2023)
- [C3: Zero-shot Text-to-SQL with ChatGPT](https://mlsanity.com/paper/2307.07306/) (2023)
- [Open Question Answering over Tables and Text](https://mlsanity.com/paper/2010.10439/) (2020)
- [Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2012.12627/) (2020)
- [A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability](https://mlsanity.com/paper/2303.13547/) (2023)
- [Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback](https://mlsanity.com/paper/2005.02539/) (2020)
- [Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering](https://mlsanity.com/paper/2108.02866/) (2021)
- [GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution](https://mlsanity.com/paper/2307.08775/) (2023)
- [Reasoning over Hybrid Chain for Table-and-Text Open Domain QA](https://mlsanity.com/paper/2201.05880/) (2022)
- [Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding](https://mlsanity.com/paper/2305.19974/) (2023)

## Built on by (most cited first, 24 of 24)

- [LoRA-LiteE: A Computationally Efficient Framework for Chatbot Preference-Tuning](https://mlsanity.com/paper/2411.09947/) (2024)
- [SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types](https://mlsanity.com/paper/2412.11757/) (2024)
- [Enhancing Customer Contact Efficiency with Graph Neural Networks in Credit Card Fraud Detection Workflow](https://mlsanity.com/paper/2504.02275/) (2025)
- [Weaver: Interweaving SQL and LLM for Table Reasoning](https://mlsanity.com/paper/2505.18961/) (2025)
- [TTQA-RS- A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarization](https://mlsanity.com/paper/2406.14732/) (2024)
- [Image-to-Image Translation with Diffusion Transformers and CLIP-Based Image Conditioning](https://mlsanity.com/paper/2505.16001/) (2025)
- [GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics](https://mlsanity.com/paper/2503.21735/) (2025)
- [Larch: Learned Query Optimization for Semantic Predicates](https://mlsanity.com/paper/2606.07923/) (2026)
- [Hybrid Querying Over Relational Databases and Large Language Models](https://mlsanity.com/paper/2408.00884/) (2024)
- [TabVer: Tabular Fact Verification with Natural Logic](https://mlsanity.com/paper/2411.01093/) (2024)
- [MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering](https://mlsanity.com/paper/2502.17253/) (2025)
- [VTS-LLM: Domain-Adaptive LLM Agent for Enhancing Awareness in Vessel Traffic Services through Natural Language](https://mlsanity.com/paper/2505.00989/) (2025)
- [Access Paths for Efficient Ordering with Large Language Models](https://mlsanity.com/paper/2509.00303/) (2025)
- [Declarative Techniques for NL Queries over Heterogeneous Data](https://mlsanity.com/paper/2510.16470/) (2025)
- [RUST-BENCH: Benchmarking LLM Reasoning on Unstructured Text within Structured Tables](https://mlsanity.com/paper/2511.04491/) (2025)
- [Laplacian Kernelized Bandit](https://mlsanity.com/paper/2601.00461/) (2026)
- [Analyzing LLM Instruction Optimization for Tabular Fact Verification](https://mlsanity.com/paper/2602.17937/) (2026)
- [SCOPE:Planning for Hybrid Querying over Clinical Trial Data](https://mlsanity.com/paper/2604.25120/) (2026)
- [Hierarchical Multi-Stage BERT Fusion Framework with Dual Attention for Enhanced Cyberbullying Detection in Social Media](https://mlsanity.com/paper/2503.00342/) (2025)
- [Play by the Type Rules: Inferring Constraints for LLM Functions in Declarative Programs](https://mlsanity.com/paper/2509.20208/) (2025)
- [Adaptive Discovery of Interpretable Audio Attributes with Multimodal LLMs for Low-Resource Classification](https://mlsanity.com/paper/2603.06991/) (2026)
- [Agentic DAG-Orchestrated Planner Framework for Multi-Modal, Multi-Hop Question Answering in Hybrid Data Lakes](https://mlsanity.com/paper/2603.14229/) (2026)
- [CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Records](https://mlsanity.com/paper/2609.07022/) (2026)
- [Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models](https://mlsanity.com/paper/2610.02576/) (2026)

## Abstract (arXiv)

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.