mlsanityData to 7 Oct 2026

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

arXiv 2402.17882 ↗First posted 27 Feb 2024cs.CLcited by 23

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

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.

Key facts. Cited by 23 papers in the map (data through 7 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.

Builds on

26 of 46 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Reasoning over Hybrid Chain for Table-and-Text Open Domain QA15 Jan

Other references · 25

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  6. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  7. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  8. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  9. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  10. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
  11. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 383
  12. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
13 more
  1. 2021Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoningcited by 376
  2. 2023Large Language Models as Tool Makerscited by 293
  3. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
  4. 2022Binding Language Models in Symbolic Languagescited by 224
  5. 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
  6. 2020Open Question Answering over Tables and Textcited by 163
  7. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
  8. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  9. 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 118
  10. 2020Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedbackcited by 44
  11. 2021Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answeringcited by 25
  12. 2023GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolutioncited by 17
  13. 2023Correcting Semantic Parses with Natural Language through Dynamic Schema Encodingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 11; 2026: 7.

23 papers.

Sort:

By area:

  1. 2024LoRA-LiteE: A Computationally Efficient Framework for Chatbot Preference-Tuningcited by 10
  2. 2024SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Typescited by 10
  3. 2025Enhancing Customer Contact Efficiency with Graph Neural Networks in Credit Card Fraud Detection Workflowcited by 8
  4. 2025Weaver: Interweaving SQL and LLM for Table Reasoningcited by 8
  5. 2024TTQA-RS- A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarizationcited by 6
  6. 2025Image-to-Image Translation with Diffusion Transformers and CLIP-Based Image Conditioningcited by 6
  7. 2025GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analyticscited by 4
  8. 2024Hybrid Querying Over Relational Databases and Large Language Modelscited by 3
  9. 2024TabVer: Tabular Fact Verification with Natural Logiccited by 3
  10. 2025MULTITAT: Benchmarking Multilingual Table-and-Text Question Answeringcited by 2
  11. 2025VTS-LLM: Domain-Adaptive LLM Agent for Enhancing Awareness in Vessel Traffic Services through Natural Languagecited by 1
  12. 2025Access Paths for Efficient Ordering with Large Language Modelscited by 1
11 more
  1. 2025Declarative Techniques for NL Queries over Heterogeneous Datacited by 1
  2. 2025RUST-BENCH: Benchmarking LLM Reasoning on Unstructured Text within Structured Tablescited by 1
  3. 2026Analyzing LLM Instruction Optimization for Tabular Fact Verificationcited by 1
  4. 2026Larch: Learned Query Optimization for Semantic Predicatescited by 1
  5. 2025Hierarchical Multi-Stage BERT Fusion Framework with Dual Attention for Enhanced Cyberbullying Detection in Social Mediacited by 0
  6. 2025Play by the Type Rules: Inferring Constraints for LLM Functions in Declarative Programscited by 0
  7. 2026Laplacian Kernelized Banditcited by 0
  8. 2026Adaptive Discovery of Interpretable Audio Attributes with Multimodal LLMs for Low-Resource Classificationcited by 0
  9. 2026Agentic DAG-Orchestrated Planner Framework for Multi-Modal, Multi-Hop Question Answering in Hybrid Data Lakescited by 0
  10. 2026SCOPE:Planning for Hybrid Querying over Clinical Trial Datacited by 0
  11. 2026CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Recordscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026QUIETT: Query-Independent Table Transformation for Robust Reasoning
  2. 2026Operads for compositional reasoning in LLMs
  3. 2025SteinerSQL: Graph-Guided Mathematical Reasoning for Text-to-SQL Generation
  4. 2025SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models
  5. 2025LogicCat: A Chain-of-Thought Text-to-SQL Benchmark for Complex Reasoning
  6. 2026MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering
  7. 2025STARQA: A Question Answering Dataset for Complex Analytical Reasoning over Structured Databases
  8. 2025From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs