# Text2SQL is Not Enough: Unifying AI and Databases with TAG

arXiv: https://arxiv.org/abs/2408.14717 · HTML: https://mlsanity.com/paper/2408.14717/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 27 Aug 2024.

## Builds on (most cited first, 19 of 19)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [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)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey](https://mlsanity.com/paper/2402.17944/) (2024)
- [Open-Domain Question Answering Goes Conversational via Question Rewriting](https://mlsanity.com/paper/2010.04898/) (2020)
- [InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks](https://mlsanity.com/paper/2401.05507/) (2024)
- [TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation](https://mlsanity.com/paper/1804.09769/) (2018)
- [Open Domain Question Answering over Tables via Dense Retrieval](https://mlsanity.com/paper/2103.12011/) (2021)
- [Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?](https://mlsanity.com/paper/2407.10956/) (2024)
- [A Declarative System for Optimizing AI Workloads](https://mlsanity.com/paper/2405.14696/) (2024)
- [Semantic Operators: A Declarative Model for Rich, AI-based Data Processing](https://mlsanity.com/paper/2407.11418/) (2024)
- [Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval](https://mlsanity.com/paper/2404.09889/) (2024)
- [Optimizing LLM Queries in Relational Data Analytics Workloads](https://mlsanity.com/paper/2403.05821/) (2024)

## Built on by (most cited first, 30 of 34)

- [Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely](https://mlsanity.com/paper/2409.14924/) (2024)
- [VideoRAG: Retrieval-Augmented Generation over Video Corpus](https://mlsanity.com/paper/2501.05874/) (2025)
- [AgenticData: An Agentic Data Analytics System for Heterogeneous Data](https://mlsanity.com/paper/2508.05002/) (2025)
- [TQA-Bench: Evaluating LLMs for Multi-Table Question Answering](https://mlsanity.com/paper/2411.19504/) (2024)
- [ELT-Bench: An End-to-End Benchmark for Evaluating AI Agents on ELT Pipelines](https://mlsanity.com/paper/2504.04808/) (2025)
- [Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB](https://mlsanity.com/paper/2504.01157/) (2025)
- [AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQL](https://mlsanity.com/paper/2508.15276/) (2025)
- [Weaver: Interweaving SQL and LLM for Table Reasoning](https://mlsanity.com/paper/2505.18961/) (2025)
- [Multilingual Text-to-SQL: Benchmarking the Limits of Language Models with Collaborative Language Agents](https://mlsanity.com/paper/2509.24405/) (2025)
- [Can LLMs Narrate Tabular Data? An Evaluation Framework for Natural Language Representations of Text-to-SQL System Outputs](https://mlsanity.com/paper/2510.23854/) (2025)
- [Arming Data Agents with Tribal Knowledge](https://mlsanity.com/paper/2602.13521/) (2026)
- [Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding](https://mlsanity.com/paper/2505.19825/) (2025)
- [SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction](https://mlsanity.com/paper/2509.00581/) (2025)
- [TransitGPT: A Generative AI-based framework for interacting with GTFS data using Large Language Models](https://mlsanity.com/paper/2412.06831/) (2024)
- [Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data](https://mlsanity.com/paper/2508.15793/) (2025)
- [NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering](https://mlsanity.com/paper/2505.19754/) (2025)
- [Querying Databases with Function Calling](https://mlsanity.com/paper/2502.00032/) (2025)
- [Balancing Content Size in RAG-Text2SQL System](https://mlsanity.com/paper/2502.15723/) (2025)
- [LLM-based Question-Answer Framework for Sensor-driven HVAC System Interaction](https://mlsanity.com/paper/2507.04748/) (2025)
- [Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence](https://mlsanity.com/paper/2507.10281/) (2025)
- [A Case for Computing on Unstructured Data](https://mlsanity.com/paper/2509.14601/) (2025)
- [HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data](https://mlsanity.com/paper/2508.18048/) (2025)
- [DRAMA: Unifying Data Retrieval and Analysis for Open-Domain Analytic Queries](https://mlsanity.com/paper/2510.27238/) (2025)
- [GraphSeek: Next-Generation Graph Analytics with LLMs](https://mlsanity.com/paper/2602.11052/) (2026)
- [Beyond Linear LLM Invocation: An Efficient and Effective Semantic Filter Paradigm](https://mlsanity.com/paper/2603.04799/) (2026)
- [Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL](https://mlsanity.com/paper/2608.15389/) (2026)
- [ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources](https://mlsanity.com/paper/2504.06271/) (2025)
- [Play by the Type Rules: Inferring Constraints for LLM Functions in Declarative Programs](https://mlsanity.com/paper/2509.20208/) (2025)
- [PaperGuide: Making Small Language-Model Paper-Reading Agents More Efficient](https://mlsanity.com/paper/2601.12988/) (2026)
- [LifeAgentBench: Benchmarking LLMs for Long-Horizon, Cross-Dimensional Lifestyle Health Reasoning](https://mlsanity.com/paper/2601.13880/) (2026)

## Abstract (arXiv)

AI systems that serve natural language questions over databases promise to unlock tremendous value. Such systems would allow users to leverage the powerful reasoning and knowledge capabilities of language models (LMs) alongside the scalable computational power of data management systems. These combined capabilities would empower users to ask arbitrary natural language questions over custom data sources. However, existing methods and benchmarks insufficiently explore this setting. Text2SQL methods focus solely on natural language questions that can be expressed in relational algebra, representing a small subset of the questions real users wish to ask. Likewise, Retrieval-Augmented Generation (RAG) considers the limited subset of queries that can be answered with point lookups to one or a few data records within the database. We propose Table-Augmented Generation (TAG), a unified and general-purpose paradigm for answering natural language questions over databases. The TAG model represents a wide range of interactions between the LM and database that have been previously unexplored and creates exciting research opportunities for leveraging the world knowledge and reasoning capabilities of LMs over data. We systematically develop benchmarks to study the TAG problem and find that standard methods answer no more than 20% of queries correctly, confirming the need for further research in this area. We release code for the benchmark at https://github.com/TAG-Research/TAG-Bench.