SQL

DAC: Decomposed Automation Correction for Text-to-SQL (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) can automate or substitute different types of tasks in software engineering.
Approach:	They evaluate the resource utilization and accuracy of Large Language Models (LLMs) in interpreting and executing natural language queries against traditional SQL within relational database management systems.
Outcome:	The proposed model can perform a variety of tasks in the software engineering process without consuming energy.

Copied to clipboard

Dingzirui Wang, Longxu Dou, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che

An LLM-Based Approach for Insight Generation in Data Analysis (2025.naacl-long)

Challenge:	Existing methods to improve text-to-SQL performance are hard to detect errors in SQL directly.
Approach:	They propose to use decomposed correction to improve text-to-SQL performance . they first detect errors based on decompose subtasks, then use it to correct them .
Outcome:	The proposed method improves text-to-SQL performance by 1.4% compared with previous methods .

Copied to clipboard

Alberto Sánchez Pérez, Alaa Boukhary, Paolo Papotti, Luis Castejón Lozano, Adam Elwood

PG-GSQL: Pointer-Generator Network with Guide Decoding for Cross-Domain Context-Dependent Text-to-SQL Generation (2020.coling-main)

Challenge:	Existing approaches to generate insightful data from databases are time-consuming and resource-intensive.
Approach:	They propose a method that leverages Large Language Models to automatically generate textual insights from databases.
Outcome:	The proposed approach generates more insightful insights than other approaches while maintaining correctness.

Copied to clipboard

Huajie Wang, Mei Li, Lei Chen

Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models (2024.findings-acl)

Challenge:	Existing approaches to text-to-SQL generation depend on interaction history and current utterances.
Approach:	They propose an encoder-decoder model based on interaction-level encoder to capture historical information of SQL query and reuse the previous SQL query tokens.
Outcome:	The proposed model outperforms the previous state-of-the-art model on the SParC benchmark . it achieves 34.0% question matching accuracy and 19.0% interaction matching accuracy .

Copied to clipboard

Yiming Wang, Zhuosheng Zhang, Pei Zhang, Baosong Yang, Rui Wang

TURING: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface (2021.acl-demo)

Challenge:	Existing methods rely on syntactically mapping natural languages to complete formal languages like Python and SQL.
Approach:	They propose to deconstruct reasoning-independent semantic information into generic symbolic representations, thereby efficiently capturing more generalized reasoning knowledge.
Outcome:	The proposed method improves in-context reasoning accuracy, learning efficiency, out-of-domain generalization, and output stability compared to the Chain-of thought technique.

Copied to clipboard

Peng Xu, Wenjie Zi, Hamidreza Shahidi, Ákos Kádár, Keyi Tang, Wei Yang, Jawad Ateeq, Harsh Barot, Meidan Alon, Yanshuai Cao

PARSQL: Enhancing Text-to-SQL through SQL Parsing and Reasoning (2025.findings-acl)

Challenge:	Existing text-to-SQL semantic parsers cannot achieve high accuracy in cross-database setting . TURING is a NLDB system that can be used to democratize data-driven insights for non-technical users .
Approach:	They propose a TURING system that provides high-precision natural language explanations of SQL queries in a beam.
Outcome:	The proposed system achieves 75.1% execution accuracy and 78.3% top-5 beam execution accuracy on the Spider validation set.

Copied to clipboard

Yaxun Dai, Haiqin Yang, Mou Hao, Pingfu Chao

SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data (2023.findings-emnlp)

Challenge:	Large language models have made significant strides in text-to-SQL tasks, but small language models struggle to accurately interpret natural language questions due to resource limitations.
Approach:	They propose a SQL parser that extracts constraints from SQL to generate sub-SQLs . they use a rule-based and LLM-based method to generate step-by-step SQL explanations based on the results .
Outcome:	The proposed framework outperforms models with the same model size on BIRD and Spider benchmarks.

Copied to clipboard

Ruoxi Sun, Sercan Arik, Rajarishi Sinha, Hootan Nakhost, Hanjun Dai, Pengcheng Yin, Tomas Pfister

Natural Language Interface for Databases Using a Dual-Encoder Model (C18-1)

Challenge:	Text-to-SQL aims to automate the process of generating SQL queries on a database from natural language text.
Approach:	They propose a method to improve few-shot prompting capabilities of Text-to-SQL for Large Language Models (LLMs) they propose 'SQlPrompt' which aims to diversify the SQL proposals during consistency selection with different prompt designs and foundation models.
Outcome:	The proposed method outperforms previous approaches for in-context learning with zero labeled data by a large margin, closing the gap with finetuning state-of-the-art with thousands of labeles.

Copied to clipboard

Ionel Alexandru Hosu, Radu Cristian Alexandru Iacob, Florin Brad, Stefan Ruseti, Traian Rebedea

ReFSQL: A Retrieval-Augmentation Framework for Text-to-SQL Generation (2023.findings-emnlp)

Challenge:	Existing approaches to train data-driven natural language interfaces for databases are limited and lack of large datasets is probably the main reason for the lack of complex machine learning approaches.
Approach:	They propose a sketch-based two-step neural model for generating structured queries based on a user’s request in natural language.
Outcome:	The proposed model improves on two recent large datasets suitable for data-driven solutions for natural language interfaces for databases.

Copied to clipboard

Kun Zhang, Xiexiong Lin, Yuanzhuo Wang, Xin Zhang, Fei Sun, Cen Jianhe, Hexiang Tan, Xuhui Jiang, Huawei Shen

PExA: Parallel Exploration Agent for Complex Text-to-SQL (2026.acl-short)

Challenge:	Existing methods that align natural language with SQL Language underestimate inherent structural characteristics of SQL and lead to structure errors.
Approach:	They propose a retrieval-argument framework that aligns natural language with SQL Language and trains one encoder-decoder-based model to fit all questions.
Outcome:	The proposed framework improves accuracy and robustness of text-to-SQL generation on five datasets.

Copied to clipboard

Tanmay Parekh, Ella Hofmann-Coyle, Shuyi Wang, Sachith Sri Ram Kothur, Srivas Prasad, Yunmo Chen

SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning (2025.findings-emnlp)

Challenge:	Recent work in text-to-SQL has explored toolaugmented LLMs, deep planning, and agentic workflows to address complex challenges.
Approach:	They validated a framework for text-to-SQL, Spider 2.0, with 70.2% execution accuracy.
Outcome:	The proposed framework achieves 70.2% execution accuracy on a state-of-the-art benchmark for text-to-SQL, Spider 2.0.

Copied to clipboard

Yuhao Zhang, Shaoming Duan, Jinhang Su, Chuanyi Liu, Peiyi Han

Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignment (2022.findings-naacl)

Challenge:	Existing methods for self-play fine-tuning do not generate new information and the large number of correct SQL queries produced by the opponent model reduces the main model’s ability to generate accurate SQL queries.
Approach:	They propose a self-play fine-tuning method tailored for the Text-to-SQL task that synthesizes high-quality fine- tuning data iteratively based on the database schema and validation feedback to enhance model performance.
Outcome:	The proposed method outperforms existing state-of-the-art methods on six open-source LLMs and five widely used benchmarks.

Copied to clipboard

Yujian Gan, Xinyun Chen, Qiuping Huang, Matthew Purver

SQLGenie: A Practical LLM based System for Reliable and Efficient SQL Generation (2025.acl-industry)

Challenge:	Existing models suffer performance degradation when evaluated on Spider-CG, even though every sub-sentence is seen during training.
Approach:	They propose a clause-level compositional example generation method to generate compositional biases from SQL clauses.
Outcome:	The proposed method improves generalization performance even on a training dataset.

Copied to clipboard

Pushpendu Ghosh, Aryan Jain, Promod Yenigalla

FD-NL2SQL: Feedback-Driven Clinical NL2SQL that Improves with Use (2026.acl-demo)

Challenge:	Large Language Models (LLMs) enable natural language to SQL conversion, but generating accurate, efficient queries is challenging due to ambiguous intent, domain knowledge requirements and database constraints.
Approach:	They propose a system for reliable SQL generation that integrates Table Onboarder, SQL Generator and Feedback Augmentation.
Outcome:	The proposed system surpasses the best single-LLM baseline by 21.5% and the strongest pipeline competitor by 5.3% on public benchmarks and internal datasets.

Copied to clipboard

Suparno Roy Chowdhury, Tejas Anvekar, Manan Roy Choudhury, Muhammad Ali Khan, Kaneez Zahra Rubab Khakwani, M Bassam Sonbol, Irbaz Bin Riaz, Vivek Gupta

CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems (2026.acl-industry)

Challenge:	Clinical trial databases are central to modern oncology research and drug development.
Approach:	FD-NL2SQL is a schema-aware clinical NL2sql assistant for SQLite-based oncology databases . it decomposes a natural-language question into predicate-level sub-questions and synthesizes executable SQL .
Outcome:	FD-NL2SQL synthesizes SQL based on decomposition, retrieved exemplars, and schema . clinical trial databases are central to modern oncology research and drug development .

Copied to clipboard

Tabinda Sarwar, Farhad Moghimifar, Cong Duy Vu Hoang, Xiaoxiao Ma, Shawn Chang Xu, Fahimeh Saleh, Poorya Zaremoodi, Avirup Sil, Katrin Kirchhoff

Dialogue Systems & Conversational Agents

Challenge:	Existing benchmarks assume a single source of ambiguity and rely on user interaction for resolution, overlooking realistic failure modes.
Approach:	They propose a framework for automatically generating an NL2SQL benchmark with multi-faceted ambiguities and diverse user behaviors.
Outcome:	The proposed framework transforms executable SQL into ambiguous queries with a conversational continuation and schema-level metadata.

Exploring Schema Generalizability of Text-to-SQL (2023.findings-acl)

Copied to clipboard

Jieyu Li, Lu Chen, Ruisheng Cao, Su Zhu, Hongshen Xu, Zhi Chen, Hanchong Zhang, Kai Yu

TableCoder: Table Extraction from Text via Reliable Code Generation (2025.acl-industry)

Challenge:	Existing text-to-SQL models are limited in their generalizability, despite their performance being over-estimated.
Approach:	They propose a framework to generate novel text-to-SQL data via automatic and synchronous (DS, SQL) pair altering.
Outcome:	The proposed framework generates text-to-SQL data via automatic and synchronous (DS, SQL) pair altering.

Copied to clipboard

Haoyu Dong, Yue Hu, Huailiang Peng, Yanan Cao

Grammar-Constrained Neural Semantic Parsing with LR Parsers (2021.findings-acl)

Challenge:	Structured table extraction from unstructured text is critical for automating data processing tasks across industries where accuracy and reliability are paramount.
Approach:	They propose a natural language-based method for extracting structured tables from text . they use Python classes or SQL statements to explicitly construct table structures .
Outcome:	The proposed method improves F1 scores and mitigates hallucinations . it integrates with standard SQL databases and Python workflows, ensuring seamless deployment .

Copied to clipboard

Artur Baranowski, Nico Hochgeschwender

Text-to-SQL Error Correction with Language Models of Code (2023.acl-short)

Challenge:	a context-free grammar can be used to enforce syntactical constraints when predicting logical forms.
Approach:	They propose a model that uses an LR parser to maintain syntactically valid sequences throughout the decoding procedure.
Outcome:	The proposed model is conceptually simpler and adds less overhead during inference compared to other approaches . it is compared with existing grammar-guided decoding frameworks and is cost-effective .

Copied to clipboard

Ziru Chen, Shijie Chen, Michael White, Raymond Mooney, Ali Payani, Jayanth Srinivasa, Yu Su, Huan Sun

Enhancing Text-to-SQL Parsing through Question Rewriting and Execution-Guided Refinement (2024.findings-acl)

Challenge:	Existing semantic parsers are not accurate enough for use in text-to-SQL parsing tasks.
Approach:	They propose to build clause-level edit models to correct SQL queries instead of token-level ones.
Outcome:	The proposed model improves the exact set match accuracy of different parsers by 2.4-6.5 and obtains up to 4.3 point absolute improvement over two strong baselines.

Copied to clipboard

Wenxin Mao, Ruiqi Wang, Jiyu Guo, Jichuan Zeng, Cuiyun Gao, Peiyi Han, Chuanyi Liu

Addressing Limitations of Encoder-Decoder Based Approach to Text-to-SQL (2022.coling-1)

Challenge:	Existing prompt engineering methods exploit database content and execution feedback to improve text-to-sql performance.
Approach:	They propose a framework for large language model-based text-to-sql task that exploits database content and execution feedback to improve execution accuracy.
Outcome:	The proposed framework improves execution accuracy and usability by 12.41% and 5.38% on four widely used benchmarks.

Copied to clipboard

Octavian Popescu, Irene Manotas, Ngoc Phuoc An Vo, Hangu Yeo, Elahe Khorashani, Vadim Sheinin

CQR-SQL: Conversational Question Reformulation Enhanced Context-Dependent Text-to-SQL Parsers (2022.findings-emnlp)

Challenge:	Existing attempts on Text-to-SQL task show a dramatic decline in performance for new databases.
Approach:	They propose a hybrid system that integrates rule-based and deep learning components to improve model accuracy.
Outcome:	The proposed system achieves double-digit percentage improvement for non-Spider databases.

Copied to clipboard

Dongling Xiao, LinZheng Chai, Qian-Wen Zhang, Zhao Yan, Zhoujun Li, Yunbo Cao

On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries (2020.findings-emnlp)

Challenge:	Existing text-to-SQL methods focus on making full use of history context, but neglect to explicitly comprehend the schema and conversational dependency.
Approach:	They propose a CQR-SQL that explicitly exploits schema and conversational dependency for multi-turn SQL parsing.
Outcome:	The proposed method exploits schema and contextual dependency for multi-turn SQL parsing.

Copied to clipboard

Tianze Shi, Chen Zhao, Jordan Boyd-Graber, Hal Daumé III, Lillian Lee

Natural SQL: Making SQL Easier to Infer from Natural Language Specifications (2021.findings-emnlp)

Challenge:	Large-scale semantic parsing datasets annotated with logical forms have enabled advances in supervised approaches.
Approach:	They propose to enrich English-language questions with SQL equivalents and alignments . they propose to use supervised attention and an auxiliary objective to disambiguate references .
Outcome:	The proposed method improves over strong baselines by 4.4% execution accuracy.

Copied to clipboard

Yujian Gan, Xinyun Chen, Jinxia Xie, Matthew Purver, John R. Woodward, John Drake, Qiaofu Zhang

What It Takes to Achieve 100% Condition Accuracy on WikiSQL (D18-1)

Challenge:	Existing models that do not support executable SQL generation can generate executable queries.
Approach:	They propose an SQL intermediate representation called Natural SQL (NatSQL) they propose to preserve the core functionalities of SQL while simplifying the queries .
Outcome:	The proposed model outperforms existing models on a text-to-SQL benchmark . it significantly improves the performance of previous models on the same dataset .

Copied to clipboard

Semih Yavuz, Izzeddin Gur, Yu Su, Xifeng Yan

Service-oriented Text-to-SQL Parsing (2020.findings-emnlp)

Challenge:	despite of its simplicity, none of the publicly reported structured query generation models can achieve an accuracy beyond 62%, which is far from enough for practical use.
Approach:	They propose a model that can achieve 88.6% condition accuracy on WikiSQL . they ask: why is the accuracy still low for such simple queries?
Outcome:	The proposed solution can reach up to 88.6% condition accuracy on the WikiSQL dataset.

Copied to clipboard

Wangsu Hu, Jilei Tian

CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (D19-1)

Challenge:	TEXT2SQL models focus on generating complex SQL query in a precise and complete fashion . current models focus only on executing complex queries in production environment . TExT2sql models are limited by human labor and limited by predefined template .
Approach:	They propose a text-to-sql parser that translates natural language utterance to SQL query . the framework enables flexibly access database than rigid API in the application .
Outcome:	The proposed model outperforms baseline models in the WikiSQL task by 13% error reduction.

Copied to clipboard

Tao Yu, Rui Zhang, Heyang Er, Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, Youxuan Jiang, Michihiro Yasunaga, Sungrok Shim, Tao Chen, Alexander Fabbri, Zifan Li, Luyao Chen, Yuwen Zhang, Shreya Dixit, Vincent Zhang, Caiming Xiong, Richard Socher, Walter Lasecki, Dragomir Radev

Database Search vs. Information Retrieval: A Novel Method for Studying Natural Language Querying of Semi-Structured Data (2020.lrec-1)

Challenge:	CoSQL is a corpus for building cross-domain, general-purpose database querying dialogue systems.
Approach:	They present a corpus for building cross-domain, general-purpose database querying dialogue systems . they use a Wizard-of-Oz collection of 3k turns plus 10k+ annotated SQL queries .
Outcome:	The proposed corpus is based on a Wizard-of-Oz dataset of 3k dialogues querying 200 complex DBs spanning 138 domains.

Copied to clipboard

Stefanie Nadig, Martin Braschler, Kurt Stockinger

Learning to Synthesize Data for Semantic Parsing (2021.naacl-main)

Challenge:	Traditionally, technicians had crafted complicated search commands in languages such as SQL to retrieve results from relational databases.
Approach:	They propose to map a database schema to a keyword-enabled relational database system that can be directly compared with information retrieval.
Outcome:	The proposed approach compares SODA, a keyword-enabled relational database system, against the Terrier information retrieval system.

Copied to clipboard

Bailin Wang, Wenpeng Yin, Xi Victoria Lin, Caiming Xiong

HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing (2022.findings-acl)

Challenge:	Existing methods for synthesizing data for semantic parsing require handcrafted rules to synthesize new programs or utterance-program pairs.
Approach:	They propose to use a (non-neural) PCFG to model the composition of programs and a BART-based translation model to map a program to an utterance to learn a generative model from existing data.
Outcome:	The proposed model can be efficiently learned from existing data on benchmarks of GeoQuery and Spider.

Copied to clipboard

Yanzhao Zheng, Haibin Wang, Baohua Dong, Xingjun Wang, Changshan Li

CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA (2026.findings-acl)

Challenge:	Recent studies focus on context-dependent text-to-SQL task but fail to exploit both . et al., 2019; xu e. al.; yu y., 2021) focus on the context-independent text to SQL task .
Approach:	They propose a history information enhanced text-to-SQL model to exploit context dependence information from history utterances and the last predicted SQL query.
Outcome:	The proposed model improves performance on two context-dependent text-to-SQL benchmarks.

Copied to clipboard

Meng Zhang, Ruochun Jin, Yuanxi Peng, Wenjing Yang, Haotian Wang, Liting Sun, Kun Hu, Silin Yang, Zhang Ke-di

Discarding the Crutches: Adaptive Parameter-Efficient Expert Meta-Learning for Continual Semantic Parsing (2025.coling-main)

Challenge:	Text-to-SQL models struggle with complex analytical tasks such as generating simple SQL queries.
Approach:	They propose a text-to-sql model that leverages Python as a procedural reasoning pivot to enhance both complex SQL generation and tabular reasoning.
Outcome:	The proposed model outperforms baseline models on six text-to-SQL benchmarks by 6.44% on average while maintaining good capability on three tableQA benchmarks.

Copied to clipboard

Ruiheng Liu, Jinyu Zhang, Yanqi Song, Yu Zhang, Bailong Yang

A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing (2020.coling-main)

Challenge:	Continual Semantic Parsing (CSP) enables parsers to generate SQL from natural language questions in task streams, using minimal annotated data to handle dynamically evolving databases in real-world scenarios.
Approach:	They propose a Adaptive PET eXpert meta-learning approach that assists experts in adaptively warming up, ensuring better model initialization.
Outcome:	The proposed method outperforms existing methods on two benchmarks and achieves superior performance without data replay or ideal settings.

Copied to clipboard

Sanxing Chen, Aidan San, Xiaodong Liu, Yangfeng Ji

SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models (2024.findings-naacl)

Challenge:	Existing methods for text-to-SQL semantic parsing require strict structured prediction due to its application scenario where the output SQL will be sent to an executor program directly.
Approach:	They propose to use schema linking and structural linking to link NL to the database schema.
Outcome:	The proposed method shows significant gains on the Spider dataset.

Copied to clipboard

Shicheng Liu, Jialiang Xu, Wesley Tjangnaka, Sina Semnani, Chen Yu, Monica Lam

DPC: Training-Free Text-to-SQL Candidate Selection via Dual-Paradigm Consistency (2026.acl-long)

Challenge:	SUQL is a conversational language that supports the generality of hybrid data access for large knowledge corpora.
Approach:	They propose a conversational agent that supports the full generality of hybrid data access for large knowledge corpora using SUQL.
Outcome:	The proposed language can handle hybrid data sources.

Copied to clipboard

Boyan Li, Ou Ocean Kun Hei, Yue Yu, Yuyu Luo

Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering (2021.acl-long)

Challenge:	Existing methods for generating SQL queries lack the ability to self-evaluate correctness without an execution oracle.
Approach:	They propose a framework that reformulates SQL selection from a probabilistic guessing task on hidden data into a deterministic verification task on visible data.
Outcome:	Experiments on BIRD and Spider show that the proposed method outperforms baselines.

Copied to clipboard

Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, Bing Xiang

Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models (2026.findings-eacl)

Challenge:	Existing generative models for open-domain question answering focus on generating direct answers from unstructured textual information, but a large amount of knowledge is stored in structured databases, and need to be accessed using query languages such as SQL.
Approach:	They propose a hybrid framework that takes both textual and tabular evidences as input and generates either direct answers or SQL queries depending on which form could better answer the question.
Outcome:	The proposed framework outperforms baseline models on OpenSQuAD datasets and can generate SQL queries on the associated databases to obtain the final answers.

Copied to clipboard

Đorđe Klisura, Joseph Khoury, Ashish Kundu, Ram Krishnan, Anthony Rios

Language Models

Challenge:	Large Language Models (LLMs) blur role boundaries by producing unrestricted responses.
Approach:	They propose to extend the Spider and BIRD text-to-SQL datasets with real-time PostgreSQl role-based policies at the table and column levels.
Outcome:	The proposed model improves refusal precision and lowers false permits.

ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning (2026.findings-acl)

Copied to clipboard

Zhensheng Wang, Xiaole Liu, Wenmian Yang, Kun Zhou, Yiquan Zhang, Weijia Jia

A Pilot Study for Chinese SQL Semantic Parsing (D19-1)

Challenge:	Existing tabular question answering systems cannot perform future-oriented numerical prediction . open-domain tabular questions are a popular approach for QA tasks .
Approach:	They propose a task that covers time-series forecasting and forecast-based reasoning scenarios using real estate data.
Outcome:	The proposed framework decomposes the problem into three collaborative roles that synthesize the results to construct a precise and consistent final answer.

Copied to clipboard

Qingkai Min, Yuefeng Shi, Yue Zhang

MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL (2025.coling-main)

Challenge:	Existing datasets to map natural language text into SQL are limited in their use in question-to-sql mapping.
Approach:	They propose to use a Chinese-based semantic parser to map natural language text into SQL.
Outcome:	The proposed dataset compares a character-based parser with a word embedding scheme for Chinese . the results show that the parsers are subject to segmentation errors and cross-lingual embedders are useful for text-to-SQL mapping.

Copied to clipboard

Xuanliang Zhang, Dingzirui Wang, Longxu Dou, Qingfu Zhu, Wanxiang Che

Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup (2022.findings-emnlp)

Challenge:	Existing multi-hop retrieval of open-domain text-to-SQL tasks is not applicable due to the tendency to retrieve tables similar to those already retrieved but irrelevant to the question.
Approach:	They propose a multi-hop table retrieval with removal task to retrieve unretrieved tables from open-domain text-to-SQL databases.
Outcome:	The proposed method improves performance 5.7% over the previous state-of-the-art methods on open-domain text-to-SQL datasets.

Copied to clipboard

Peng Shi, Linfeng Song, Lifeng Jin, Haitao Mi, He Bai, Jimmy Lin, Dong Yu

Multilinguality

Challenge:	Experimental results show that Rex can benefit from cross-lingual training and improve the effectiveness of semantic parsers.
Approach:	They propose a Representation Mixup Framework for effectively exploiting translations in the cross-lingual Text-to-SQL task.
Outcome:	The proposed framework can benefit from cross-lingual training and improve the effectiveness of semantic parsers, achieving state-of-the-art performance.

QBridge: Bridging Natural Language and SQL via Gold Query Rewriting with Agentic Refinement (2026.acl-long)

Copied to clipboard

Zhensheng Luo, Sai Wu, Yuan Qiu, Chang Yao, Gang Chen, Xiu Tang

UCS-SQL: Uniting Content and Structure for Enhanced Semantic Bridging In Text-to-SQL (2025.findings-acl)

Challenge:	Natural language to SQL (NL2SQL) is an intuitive interface for querying structured data . but real user questions are noisy, ambiguous, and weakly grounded to database semantics.
Approach:	They propose an agentic feedback-driven NL2SQL framework that bridges natural language and SQL via Gold Query.
Outcome:	The proposed framework outperforms strong prompting and agentic baselines on spider, BIRD, and three robustness variants on NL2SQL.

Copied to clipboard

Zhenhe Wu, Zhongqiu Li, JieZhangChinaTele JieZhangChinaTele, Zhongjiang He, Jian Yang, Yu Zhao, Ruiyu Fang, Bing Wang, Hongyan Xie, Shuangyong Song, Zhoujun Li

CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset (2023.findings-acl)

Challenge:	Existing methods overlook the challenge of effectively transforming structure information from NL to SQL.
Approach:	They propose a text-to-SQL framework that unites content and structure pipes to bridge the gap between NL and SQL.
Outcome:	The proposed framework bridges the gap between natural language questions and SQL by combining content and structure pipes.

Copied to clipboard

Hanchong Zhang, Jieyu Li, Lu Chen, Ruisheng Cao, Yunyan Zhang, Yu Huang, Yefeng Zheng, Kai Yu

Benchmarking and Improving Text-to-SQL Generation under Ambiguity (2023.emnlp-main)

Challenge:	a cross-domain text-to-SQL task aims to parse user questions into SQL on complete unseen databases . a single-domain task evaluates the performance on identical databases based on the same domain .
Approach:	They propose a cross-domain text-to-SQL task that parses user questions into SQL on unseen databases.
Outcome:	The proposed system can parse user questions into SQL on complete unseen databases.

Copied to clipboard

Adithya Bhaskar, Tushar Tomar, Ashutosh Sathe, Sunita Sarawagi

Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation (P19-1)

Challenge:	Existing decoding algorithms treat SQL queries as a string and produce unhelpful token-level diversity in the top-k.
Approach:	They propose a benchmarking algorithm that generates all SQLs in top-k ranked outputs . they use plan-based template generation and constrained infilling to bridge this gap .
Outcome:	The proposed algorithm is 2.5 times more effective than state-of-the-art models at generating all candidate SQLs in the top-k ranked outputs.

Copied to clipboard

Jiaqi Guo, Zecheng Zhan, Yan Gao, Yan Xiao, Jian-Guang Lou, Ting Liu, Dongmei Zhang

Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing (P19-1)

Challenge:	IRNet synthesizes SQL queries in an end-to-end manner, but it yields unsatisfactory performance on public benchmarks.
Approach:	They propose a neural approach called IRNet for complex and cross-domain Text-to-SQL.
Outcome:	IRNet achieves 46.7% accuracy on the Spider benchmark, a 19.5% improvement over state-of-the-art approaches.

Copied to clipboard

Ben Bogin, Jonathan Berant, Matt Gardner

SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers (2022.coling-1)

Challenge:	Semantic parsing to SQL has largely ignored the structure of the database schema . a recent study used a simple DB that was observed at both training and test time.
Approach:	They propose a semantic parser where the schema structure is encoded with a graph neural network and used at both encoding and decoding time.
Outcome:	The proposed parser improves from 33.8% to 39.4%, dramatically above the current state of the art, which is at 19.7%.

Copied to clipboard

Bowen Qin, Lihan Wang, Binyuan Hui, Bowen Li, Xiangpeng Wei, Binhua Li, Fei Huang, Luo Si, Min Yang, Yongbin Li

Efficient (Soft) Q-Learning for Text Generation with Limited Good Data (2022.findings-emnlp)

Challenge:	Existing methods that learn from multiple semantically-equivalent questions are limited to one-to-one mapping .
Approach:	They propose a constraint to explore the underlying complementary semantic information among multiple semantically-equivalent questions and learn robust feature representations with reduced spurious associations.
Outcome:	The proposed method outperforms strong competitors and achieves state-of-the-art results on five benchmark datasets.

Copied to clipboard

Han Guo, Bowen Tan, Zhengzhong Liu, Eric Xing, Zhiting Hu

Responsible & Trustworthy NLP

Challenge:	Maximum likelihood estimation (MLE) is the predominant method for training text generation models.
Approach:	They propose a new RL formulation for text generation from the soft Q-learning perspective using path consistency learning to combine the best of on-/off-policy updates and learn effectively from sparse reward.
Outcome:	The proposed approach outperforms MLE and previous RL methods in a wide range of tasks.

Semantic Captioning: Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning for SQL2Text (2025.coling-main)

Copied to clipboard

Ali Al Lawati, Jason Lucas, Prasenjit Mitra

Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions (D19-1)

Challenge:	Large Language Models (LLMs) have shown remarkable performance in various NLP tasks, including semantic parsing, which translates natural language into formal code representations.
Approach:	They propose a semantic captioning task to repurpose semantic parsing datasets for semantic captions.
Outcome:	The proposed model outperforms random selection and other methods by 39% on BLEU score.

Copied to clipboard

Rui Zhang, Tao Yu, Heyang Er, Sungrok Shim, Eric Xue, Xi Victoria Lin, Tianze Shi, Caiming Xiong, Richard Socher, Dragomir Radev

Enhancing Text-to-SQL Capabilities of Large Language Models through Tailored Promptings (2024.lrec-main)

Challenge:	Generating SQL queries from user utterances is an important task to help end users acquire information from databases.
Approach:	They propose a context-dependent text-to-SQL generation task that edits previous queries . they use an utterance-table encoder and a table-aware decoder to incorporate context .
Outcome:	The proposed model is flexible to change individual tokens and robust to error propagation.

Copied to clipboard

Zhao Tan, Xiping Liu, Qing Shu, Xi Li, Changxuan Wan, Dexi Liu, Qizhi Wan, Guoqiong Liao

Learning Programmatic Idioms for Scalable Semantic Parsing (D19-1)

Challenge:	Large language models with prompting have achieved encouraging results on many natural language processing tasks due to the absence of task-tailored promptings.
Approach:	They propose three promptings specifically designed for Text-to-SQL: SL-prompt, CC-promped, and SL+CC prompt.
Outcome:	The proposed promptings achieve execution accuracy of 86.2% and test-suite accuracy of 76% . the granularity of schema linking and the order of clause generation have great impact on performance, which are considered little in previous research.

Copied to clipboard

Srinivasan Iyer, Alvin Cheung, Luke Zettlemoyer

LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domains (2025.findings-emnlp)

Challenge:	In state-of-the-art semantic parsers map natural language instructions to source code . idioms improve the accuracy of semantic parses, allowing for faster decoding .
Approach:	They propose an iterative method to extract code idioms from large source code corpora . they use most-frequent subtrees of their syntax trees to train semantic parsers to apply them .
Outcome:	The proposed method improves the state-of-the-art semantic parsers' accuracy and training time by more than 50%.

Copied to clipboard

Liyao Li, Jiaming Tian, Hao Chen, Wentao Ye, Chao Ye, Haobo Wang, Ningtao Wang, Xing Fu, Gang Chen, Junbo Zhao

Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM (2024.findings-acl)

Challenge:	Evaluating 52 LLMs reveals that only the strongest models maintain robust performance under increasing context lengths and format diversity.
Approach:	They propose a benchmark for evaluating long-context reasoning over semi-structured tables across diverse formats, tasks, and domains.
Outcome:	The proposed model outperforms compression-based approaches on tasks requiring semantic integration.

Copied to clipboard

Zijin Hong, Zheng Yuan, Hao Chen, Qinggang Zhang, Feiran Huang, Xiao Huang

Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward (2025.findings-emnlp)

Challenge:	Existing methods for Generating accurate SQL queries for user questions rely on the capability of large language models (LLMs) however, some knowledge is not explicitly included in the database schema and user question or has been learned by LLMs.
Approach:	They propose a Knowledge-to-SQL framework that employs tailored Data Expert LLM (DELLM) to provide helpful knowledge for all text-to SQL models.
Outcome:	The proposed framework improves the state-of-the-art approaches for text-to-SQL tasks by leveraging a data expert LLM (DELLM) to provide useful knowledge for all text- to-SqL models.

Copied to clipboard

Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, Xing Chen

Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing (2021.emnlp-main)

Challenge:	Existing methods to enhance performance of large language models (LLMs) on Text-to-SQL tasks rely on execution-based or LLM-based reward models.
Approach:	They propose a reward model framework for RL-based Text-to-SQL that employs the GMNScore outcome reward model.
Outcome:	The proposed reward model outperforms existing reward models on standard benchmarks including Spider and BIRD.

Copied to clipboard

Kun Wu, Lijie Wang, Zhenghua Li, Ao Zhang, Xinyan Xiao, Hua Wu, Min Zhang, Haifeng Wang

SPARQLing Database Queries from Intermediate Question Decompositions (2021.emnlp-main)

Challenge:	Existing approaches to parse text-to-SQL data are lacking labeled data for unseen evaluation databases.
Approach:	They propose a framework for enhancing SQL queries by automatically producing large numbers of SQL queries based on an abstract syntax tree grammar.
Outcome:	The proposed framework can produce high-quality natural language questions over strong baselines.

Copied to clipboard

Irina Saparina, Anton Osokin

Dataset and Enhanced Model for Eligibility Criteria-to-SQL Semantic Parsing (2020.lrec-1)

Challenge:	Using annotated datasets is difficult as it requires query-language expertise.
Approach:	They propose a crowdsourcing pipeline to annotate natural language questions using intermediate question representations.
Outcome:	The proposed pipeline reduces the burden of annotating a large dataset with queries by using intermediate question representations.

Copied to clipboard

Xiaojing Yu, Tianlong Chen, Zhengjie Yu, Huiyu Li, Yang Yang, Xiaoqian Jiang, Anxiao Jiang

DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models (2024.emnlp-main)

Challenge:	Clinical trials require that patients meet eligibility criteria to ensure safety and effectiveness of studies.
Approach:	They propose a dataset that includes the first-of-its-kind eligibility-criteria corpus and queries for criteria-to-sql . they propose 'neuro semantic parser' which can translate eligibility criteria to executable SQL queries .
Outcome:	The proposed parser outperforms existing state-of-the-art general-purpose models while highlighting the challenges presented by the new dataset.

Copied to clipboard

Yiming Huang, Jianwen Luo, Yan Yu, Yitong Zhang, Fangyu Lei, Yifan Wei, Shizhu He, Lifu Huang, Xiao Liu, Jun Zhao, Kang Liu

PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models (2021.emnlp-main)

Challenge:	DA-Code is a code generation benchmark designed to assess LLMs on agent-based data science tasks.
Approach:	They propose a code generation benchmark specifically designed for LLMs on agent-based data science tasks.
Outcome:	The benchmark performs better than existing frameworks, but lacks accuracy . it is based on real-world data, and includes examples that cover a wide range of tasks .

Copied to clipboard

Torsten Scholak, Nathan Schucher, Dzmitry Bahdanau

Language Models

Challenge:	Large pre-trained language models for textual data have an unconstrained output space . when fine-tuned to target constrained formal languages like SQL, these models often generate invalid code, rendering it unusable.
Approach:	They propose a method for constraining auto-regressive decoders of language models through incremental parsing.
Outcome:	The proposed method can find valid output sequences by rejecting inadmissible tokens . it can be used on Spider and CoSQL text-to-SQl translation tasks .

R3-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL (2024.findings-emnlp)

Copied to clipboard

Yuhang Zhou, Yu He, Siyu Tian, Yuchen Ni, Zhangyue Yin, Xiang Liu, Chuanjun Ji, Sen Liu, Xipeng Qiu, Guangnan Ye, Hongfeng Chai

XSemPLR: Cross-Lingual Semantic Parsing in Multiple Natural Languages and Meaning Representations (2023.acl-long)

Challenge:	Adapting existing approaches for converting natural language to SQL encounters hurdles due to distinct nature of GQL compared to SQL.
Approach:	They propose a method that integrates both small and large Foundation Models for ranking, rewriting, and refining tasks.
Outcome:	The proposed approach integrates both small and large Foundation Models for ranking, rewriting, and refining tasks while capitalizing on the superior generalization and query generation prowess of larger models for the final transformation of natural language queries into GQL formats.

Copied to clipboard

Yusen Zhang, Jun Wang, Zhiguo Wang, Rui Zhang

SQUAB: Evaluating LLM robustness to Ambiguous and Unanswerable Questions in Semantic Parsing (2025.emnlp-main)

Challenge:	Existing models for cross-lingual semantic parsing are not able to perform tasks on a wide range of datasets.
Approach:	They propose a benchmark for cross-lingual semantic parsing that uses 22 natural languages and 8 meaning representations to translate queries into MRs.
Outcome:	The proposed benchmarks cover 22 natural languages and 8 meaning representations on 164 domains and 5 tasks covering a wide range of multilingual language models.

Copied to clipboard

Simone Papicchio, Luca Cagliero, Paolo Papotti

Robustness in NLP

Challenge:	Practical user questions often deviate from ideal conditions, challenging the applicability of existing benchmarks.
Approach:	They propose an automatic dataset generator of Ambiguous and Unanswerable questions that generates complex, annotated SP tests using a blend of SQL and LLM capabilities.
Outcome:	The proposed framework reduces test generation costs by up to 99% while aligning with real-world question patterns.

Semantic Decomposition of Question and SQL for Text-to-SQL Parsing (2023.findings-emnlp)

Copied to clipboard

Ben Eyal, Moran Mahabi, Ophir Haroche, Amir Bachar, Michael Elhadad

Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations (2023.emnlp-main)

Challenge:	Existing text-to-SQL models for complex queries are limited by the syntactic complexity of SQL.
Approach:	They propose a question decomposition language that decomposes SQL queries into simple and regular sub-queries.
Outcome:	The proposed language decomposes SQL queries into simple and regular sub-queries . it is more accessible to non-experts for complex queries, enabling interpretable output .

Copied to clipboard

Yuan Tian, Zheng Zhang, Zheng Ning, Toby Li, Jonathan K. Kummerfeld, Tianyi Zhang

Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion (2025.findings-emnlp)

Challenge:	Existing approaches to generate SQL from natural language are still making many mistakes . a new interaction mechanism allows users to edit a step-by-step explanation of a query to fix errors.
Approach:	They propose a mechanism that allows users to edit a step-by-step explanation of a query to fix errors.
Outcome:	The proposed approach can achieve better performance than multiple SOTA approaches on multiple datasets and 24 participants.

Copied to clipboard

Yujian Liu, Jiabao Ji, Tong Yu, Ryan A. Rossi, Sungchul Kim, Handong Zhao, Ritwik Sinha, Yang Zhang, Shiyu Chang

LIST: Linearly Incremental SQL Translator for Single-Hop Reasoning, Generation and Verification (2025.findings-acl)

Challenge:	Existing methods to integrate external information into a given table neglect the structured nature of the table.
Approach:	They propose a simple yet effective method to integrate external information into a given table by first building an augmenting table and then generating a SQL query over the two tables to answer the question.
Outcome:	The proposed method outperforms strong baselines on three table QA benchmarks.

Copied to clipboard

Kaiyuan Guan, Ruoxin Li, Xudong Guo, Zhenning Huang, Xudong Weng, Hehuan Liu, Zheng Wei, Zang Li

DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction (2025.findings-emnlp)

Challenge:	Existing schema linking methods are not able to handle complex SQL queries.
Approach:	They propose a new algorithm that transforms SQL queries into grammatically verifiable sub-queries which are arranged sequentially to reflect single-hop reasoning steps.
Outcome:	The proposed algorithm achieves significant performance gains on the BIRD dataset and surpasses schema linking methods at comparable or better cost.

Copied to clipboard

Jian Chen, Zhenyan Chen, Xuming Hu, Peilin Zhou, Yining Hua, Han Fang, Cissy Hing Yee Choy, Xinmei Ke, Jingfeng Luo, Zixuan Yuan

Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL (2026.findings-acl)

Challenge:	NL2SQL provides a model-centric paradigm that simplifies database access for non-technical users . challenges such as inaccurate task decomposition and keyword extraction remain major bottlenecks .
Approach:	They propose a RAG-based NL2SQL pipeline that employs three modules for query understanding, entity retrieval, and generation to improve SQL generation accuracy.
Outcome:	The proposed pipeline improves the accuracy of query generation on BIRD and Spider datasets.

Copied to clipboard

Zhewei Yao, Guoheng Sun, Łukasz Borchmann, Zheyu Shen, Minghang Deng, Bohan Zhai, Hao Zhang, Ang Li, Yuxiong He

Weaver: Interweaving SQL and LLM for Table Reasoning (2025.emnlp-main)

Challenge:	Translating natural language questions into SQL is a core challenge in natural language understanding and human-computer interaction.
Approach:	They propose a reinforcement learning framework and model family to generate accurate, executable SQL using a lightweight reward signal based solely on execution correctness.
Outcome:	The proposed framework outperforms previous versions of 70B-class systems and achieves state-of-the-art execution accuracy across six diverse Text2SQL benchmarks.

Copied to clipboard

Rohit Khoja, Devanshu Gupta, Yanjie Fu, Dan Roth, Vivek Gupta

MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training (2026.acl-long)

Challenge:	Existing approaches that combine SQL and LLM rely on rigid workflows . Tables play a critical role across various domains such as finance, healthcare and scientific research .
Approach:	Weaver is a modular pipeline that integrates SQL and LLM for table-based question answering.
Outcome:	Weaver outperforms state-of-the-art methods on four Table QA datasets.

Copied to clipboard

Taicheng Guo, Hai Wang, Chaochun Liu, Mohsen Golalikhani, Xin Chen, Xiangliang Zhang, Chandan K. Reddy

STARQA: A Question Answering Dataset for Complex Analytical Reasoning over Structured Databases (2025.emnlp-main)

Challenge:	Existing systems for multi-turn Text-to-SQL are limited to a short-horizon paradigm, generating a query per turn without execution, explicit verification, and refinement, which leads to non-executable or incoherent outputs.
Approach:	They propose to train an agentic training framework for long-horizon multi-turn Text-to-SQL that uses a Markov Decision Process to generate a query per turn without execution, explicit verification, and refinement.
Outcome:	Experiments on CoSQL and SParC show that MTSQL-R1 consistently outperforms strong baselines, highlighting the importance of environment-driven verification and memory-guided refinement for conversational semantic parsing.

Copied to clipboard

Mounica Maddela, Lingjue Xie, Daniel Preotiuc-Pietro, null Mausam

R3-SQL: Ranking Reward and Resampling for Text-to-SQL (2026.findings-acl)

Challenge:	Existing Text2SQL systems do not support SQL analysts in their primary work of performing complex analytics on specialized databases.
Approach:	They propose to decompose STARQA questions using SQL and Python to perform reasoning on specialized relational databases.
Outcome:	The proposed approach decomposes the task through a combination of SQL and Python, and achieves better performance on the more difficult questions.

Copied to clipboard

Hojae Han, Yeonseok Jeong, Seung-won Hwang, Zhewei Yao, Yuxiong He