Lune

ACL Findings2024

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

Parker Glenn, Parag Dakle, Liang Wang, Preethi Raghavan

Abstract

Many existing end-to-end systems for hybrid question answering tasks can 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 BLEND-SQL query. Notably, we show that BLEND-SQL can scale to massive datasets and improve the performance of end-to-end systems while using 35% fewer prompt tokens. Our code is available and installable as a package at github.com/parkervg/blendsql.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Gorilla: Large Language Model Connected with Massive APIs cites Toolformer: Language Models Can Teach Themselves to Use Tools
  • Gorilla: Large Language Model Connected with Massive APIs cites HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
  • Gorilla: Large Language Model Connected with Massive APIs cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models
  • HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face cites Toolformer: Language Models Can Teach Themselves to Use Tools
  • HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement LearningJuntong Ni, Shiyu Wang, Qi He, Ming Jin et al.ACL 2026 · 8 citations
  2. Exploring Hybrid Question Answering via Program-based PromptingQi Shi, Han Cui, Haofeng Wang, Qingfu Zhu et al.ACL 2024 · 3 citations
  3. Weaver: Interweaving SQL and LLM for Table ReasoningRohit Khoja, Devanshu Gupta, Yanjie Fu, Dan Roth et al.EMNLP 2025 · 1 citation
  4. Laplacian Kernelized BanditShuang Wu, Arash A. AminiICLR 2026

Builds on21

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
  3. Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
  4. HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging FaceYongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li et al.NeurIPS 2023 · 1,778 citations
  5. Gorilla: Large Language Model Connected with Massive APIsShishir G. Patil, Tianjun Zhang, Xin Wang, Joseph E. GonzalezNeurIPS 2024 · 1,715 citations

Related papers

  1. Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question AnsweringAlexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu et al.ACL 2021
  2. SQLPrompt: In-Context Text-to-SQL with Minimal Labeled DataRuoxi Sun, Sercan Ö. Arik, Rajarishi Sinha, Hootan Nakhost et al.EMNLP Findings 2023 · 18 citations
  3. STARQA: A Question Answering Dataset for Complex Analytical Reasoning over Structured DatabasesMounica Maddela, Lingjue Xie, Daniel Preotiuc-Pietro, MausamEMNLP 2025
  4. CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQAMeng Zhang, Ruochun Jin, Yuanxi Peng, Wenjing Yang et al.ACL Findings 2026
  5. LIST: Linearly Incremental SQL Translator for Single-Hop Reasoning, Generation and VerificationKaiyuan Guan, Ruoxin Li, Xudong Guo, Zhenning Huang et al.ACL Findings 2025
Dusk over the sea between two cliffs drawn in fine vertical lines