A new top score: Advancing Text-to-SQL on the BIRD benchmark
The text discusses the advancement of text-to-SQL (NL2SQL) capabilities, where natural language translates into SQL queries, facilitating data access. Google Cloud achieved a state-of-the-art sco…
Telegram AI Digest
#ai #gemini #geminiai
The text discusses the advancement of text-to-SQL (NL2SQL) capabilities, where natural language translates into SQL queries, facilitating data access. Google Cloud achieved a state-of-the-art sco…
Telegram AI Digest
#ai #gemini #geminiai
A new top score: Advancing Text-to-SQL on the BIRD benchmark
The text discusses the advancement of text-to-SQL (NL2SQL) capabilities, where natural language translates into SQL queries, facilitating data access. Google Cloud achieved a state-of-the-art score on the BIRD benchmark, using a single model. The BIRD benchmark assesses NL2SQL solutions, focusing on execution-verified accuracy across diverse databases. This advancement, built upon a specialized Gemini model, improves customer experience in various data services. This includes enhanced natural language querying within AlloyDB AI and conversational analytics in BigQuery. Developers can use AI assistance, such as Google Code Assist, for efficient SQL code generation. The success stems from specialized model tuning including rigorous data filtering and multitask learning. Self-consistency at test time further boosted the model's accuracy. This improved model provides a strong foundation for future advancements in data services. It enables a more robust baseline for text-to-SQL capabilities. The improved model is now driving innovation in Google Data Cloud products, as exemplified by enhanced natural language querying within AlloyDB and BigQuery.
cloud.google.com
November 15, 2025 at 6:19 PM
A new top score: Advancing Text-to-SQL on the BIRD benchmark
The text discusses the advancement of text-to-SQL (NL2SQL) capabilities, where natural language translates into SQL queries, facilitating data access. Google Cloud achieved a state-of-the-art sco…
Telegram AI Digest
#ai #gemini #geminiai
The text discusses the advancement of text-to-SQL (NL2SQL) capabilities, where natural language translates into SQL queries, facilitating data access. Google Cloud achieved a state-of-the-art sco…
Telegram AI Digest
#ai #gemini #geminiai
to generate the SQL query.
However, existing NL2SQL techniques miss a key opportunity which is present in real-world settings: NL2SQL is typically applied on existing databases which have already served many SQL queries in the past. The past query [3/6 of https://arxiv.org/abs/2505.23039v1]
However, existing NL2SQL techniques miss a key opportunity which is present in real-world settings: NL2SQL is typically applied on existing databases which have already served many SQL queries in the past. The past query [3/6 of https://arxiv.org/abs/2505.23039v1]
May 30, 2025 at 5:55 AM
to generate the SQL query.
However, existing NL2SQL techniques miss a key opportunity which is present in real-world settings: NL2SQL is typically applied on existing databases which have already served many SQL queries in the past. The past query [3/6 of https://arxiv.org/abs/2505.23039v1]
However, existing NL2SQL techniques miss a key opportunity which is present in real-world settings: NL2SQL is typically applied on existing databases which have already served many SQL queries in the past. The past query [3/6 of https://arxiv.org/abs/2505.23039v1]
Assinei pra mime so preciso saber como plugo ele no meu sistema nl2sql
January 30, 2025 at 6:57 PM
Assinei pra mime so preciso saber como plugo ele no meu sistema nl2sql
[2024/08/12 ~ 08/18] 이번 주의 주요 ML 논문 (Top ML Papers of the Week)
(by 9bow님)
https://d.ptln.kr/5061
#paper #top-ml-papers-of-the-week #survey-paper #text-to-sql #graph-rag #grok-2 #vector-rag #medical-graph-rag #nl2sql #rstar #hybrid-rag #ai-scientist #ragchecker #efficientrag #longwriter
(by 9bow님)
https://d.ptln.kr/5061
#paper #top-ml-papers-of-the-week #survey-paper #text-to-sql #graph-rag #grok-2 #vector-rag #medical-graph-rag #nl2sql #rstar #hybrid-rag #ai-scientist #ragchecker #efficientrag #longwriter
[2024/08/12 ~ 08/18] 이번 주의 주요 ML 논문 (Top ML Papers of the Week)
[2024/08/12 ~ 08/18] 이번 주의 주요 ML 논문 (Top ML Papers of the Week) PyTorchKR🔥🇰🇷 🤔💬 이번 주에 선정된 논문 목록을 보면, 특히 자연어 처리(NLP)와 관련된 연구가 두드러집니다. 또한, 많은 논문들이 복합적 접근법(multimodal)과 정보 검색(retrieval)에 중점을 두고 있는 것이 눈에 띕니다. 첫 번째로, 대부분의 논문이 자연어 처리와 관련이 있습니다. 'LongWriter', 'EfficientRAG', 'RAGChecker', 'HybridRAG', 'MedGraphRAG', 'Survey of NL2QL' 등의 논문들은 자연어 처리를 다양한 방식으로 다루고 있으며, 그중에서도 복합적 검색 알고리즘을 통해 정보를 효율적으로 찾고 활용하는 문제를 중점적으로 다루고 있습니다. 이는 NLP가 여전히 인공지능 연구의 핫토픽임을 보여줍니다. 두 번...
d.ptln.kr
August 19, 2024 at 2:09 PM
[2024/08/12 ~ 08/18] 이번 주의 주요 ML 논문 (Top ML Papers of the Week)
(by 9bow님)
https://d.ptln.kr/5061
#paper #top-ml-papers-of-the-week #survey-paper #text-to-sql #graph-rag #grok-2 #vector-rag #medical-graph-rag #nl2sql #rstar #hybrid-rag #ai-scientist #ragchecker #efficientrag #longwriter
(by 9bow님)
https://d.ptln.kr/5061
#paper #top-ml-papers-of-the-week #survey-paper #text-to-sql #graph-rag #grok-2 #vector-rag #medical-graph-rag #nl2sql #rstar #hybrid-rag #ai-scientist #ragchecker #efficientrag #longwriter
Mohammadtaher Safarzadeh, Afshin Oroojlooyjadid, Dan Roth
Evaluating NL2SQL via SQL2NL
https://arxiv.org/abs/2509.04657
Evaluating NL2SQL via SQL2NL
https://arxiv.org/abs/2509.04657
September 8, 2025 at 7:00 AM
Mohammadtaher Safarzadeh, Afshin Oroojlooyjadid, Dan Roth
Evaluating NL2SQL via SQL2NL
https://arxiv.org/abs/2509.04657
Evaluating NL2SQL via SQL2NL
https://arxiv.org/abs/2509.04657
Marianne Menglin Liu, Sai Ashish Somayajula, Syed Fahad Allam Shah, Sujith Ravi, Dan Roth
OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning
https://arxiv.org/abs/2510.23870
OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning
https://arxiv.org/abs/2510.23870
October 29, 2025 at 8:47 AM
Marianne Menglin Liu, Sai Ashish Somayajula, Syed Fahad Allam Shah, Sujith Ravi, Dan Roth
OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning
https://arxiv.org/abs/2510.23870
OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning
https://arxiv.org/abs/2510.23870
performance in this domain. However, existing NL2SQL methods predominantly rely on closed-source LLMs leveraging prompt engineering, while open-source models typically require fine-tuning to acquire domain-specific knowledge. Despite these efforts, [2/7 of https://arxiv.org/abs/2504.02327v1]
April 4, 2025 at 5:57 AM
performance in this domain. However, existing NL2SQL methods predominantly rely on closed-source LLMs leveraging prompt engineering, while open-source models typically require fine-tuning to acquire domain-specific knowledge. Despite these efforts, [2/7 of https://arxiv.org/abs/2504.02327v1]
[ainet] AI기업[웹케시그룹 AI 전문 사내벤처 ‘다큐브’ ] Spider 2.0 국제 벤치마크서 NL2SQL 세계 1위 달성 자연어 기반 SQL 변환 기술로 글로벌 기술력 입증
www.ainet.link/21599
www.ainet.link/21599
AI기업[웹케시그룹 AI 전문 사내벤처 ‘다큐브’ ] Spider 2.0 국제 벤치마크서 NL2SQL 세계 1위 달성 자연어 기반 SQL 변환 기술로 글로벌 기술력 입증
웹케시그룹AI전문사내벤처‘다큐브’Spider2.0국제벤치마크서NL2SQL세계1위달성자연어기반SQL변환기술로글로벌기술력입증마드라스체크에이어웹케시그
www.ainet.link
July 8, 2025 at 10:46 AM
[ainet] AI기업[웹케시그룹 AI 전문 사내벤처 ‘다큐브’ ] Spider 2.0 국제 벤치마크서 NL2SQL 세계 1위 달성 자연어 기반 SQL 변환 기술로 글로벌 기술력 입증
www.ainet.link/21599
www.ainet.link/21599
Dai Quoc Nguyen, Cong Duy Vu Hoang, Duy Vu, Gioacchino Tangari, Thanh Tien Vu, Don Dharmasiri, Yuan-Fang Li, Long Duong
SQLong: Enhanced NL2SQL for Longer Contexts with LLMs
https://arxiv.org/abs/2502.16747
SQLong: Enhanced NL2SQL for Longer Contexts with LLMs
https://arxiv.org/abs/2502.16747
February 25, 2025 at 11:39 AM
Dai Quoc Nguyen, Cong Duy Vu Hoang, Duy Vu, Gioacchino Tangari, Thanh Tien Vu, Don Dharmasiri, Yuan-Fang Li, Long Duong
SQLong: Enhanced NL2SQL for Longer Contexts with LLMs
https://arxiv.org/abs/2502.16747
SQLong: Enhanced NL2SQL for Longer Contexts with LLMs
https://arxiv.org/abs/2502.16747
arXiv:2505.20591v1 Announce Type: new
Abstract: NL2SQL approaches have greatly benefited from the impressive capabilities of large language models (LLMs). In particular, bootstrapping an NL2SQL system for a specific domain can be as simple as [1/7 of https://arxiv.org/abs/2505.20591v1]
Abstract: NL2SQL approaches have greatly benefited from the impressive capabilities of large language models (LLMs). In particular, bootstrapping an NL2SQL system for a specific domain can be as simple as [1/7 of https://arxiv.org/abs/2505.20591v1]
May 28, 2025 at 6:01 AM
arXiv:2505.20591v1 Announce Type: new
Abstract: NL2SQL approaches have greatly benefited from the impressive capabilities of large language models (LLMs). In particular, bootstrapping an NL2SQL system for a specific domain can be as simple as [1/7 of https://arxiv.org/abs/2505.20591v1]
Abstract: NL2SQL approaches have greatly benefited from the impressive capabilities of large language models (LLMs). In particular, bootstrapping an NL2SQL system for a specific domain can be as simple as [1/7 of https://arxiv.org/abs/2505.20591v1]
detection, achieving an average detection accuracy of only 75.16%. Despite this, the models were able to successfully detect 106 errors (accounting for 6.91%) in the widely-used NL2SQL dataset, BIRD, which were previously annotation errors in the [6/7 of https://arxiv.org/abs/2503.11984v1]
March 18, 2025 at 5:55 AM
detection, achieving an average detection accuracy of only 75.16%. Despite this, the models were able to successfully detect 106 errors (accounting for 6.91%) in the widely-used NL2SQL dataset, BIRD, which were previously annotation errors in the [6/7 of https://arxiv.org/abs/2503.11984v1]
visualizations. While recent advancements in large language models (LLMs) have significantly improved NL2SQL accuracy, schema ambiguity remains a major challenge in enterprise environments with complex schemas, where multiple tables and columns with [2/5 of https://arxiv.org/abs/2505.19302v1]
May 27, 2025 at 5:56 AM
visualizations. While recent advancements in large language models (LLMs) have significantly improved NL2SQL accuracy, schema ambiguity remains a major challenge in enterprise environments with complex schemas, where multiple tables and columns with [2/5 of https://arxiv.org/abs/2505.19302v1]
Marianne Menglin Liu, Sai Ashish Somayajula, Syed Fahad Allam Shah, Sujith Ravi, Dan Roth: OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning https://arxiv.org/abs/2510.23870 https://arxiv.org/pdf/2510.23870 https://arxiv.org/html/2510.23870
October 29, 2025 at 6:30 AM
Marianne Menglin Liu, Sai Ashish Somayajula, Syed Fahad Allam Shah, Sujith Ravi, Dan Roth: OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning https://arxiv.org/abs/2510.23870 https://arxiv.org/pdf/2510.23870 https://arxiv.org/html/2510.23870
Новый рекорд: Улучшение Text-to-SQL на бенчмарке BIRD
В тексте обсуждается развитие возможностей преобразования текста в SQL (NL2SQL), где естественный язык преобразуется в SQL-запросы, облегчая доступ к данным. Компания Google Cloud получила самую современную оценк…
Telegram ИИ Дайджест
#ai #news
В тексте обсуждается развитие возможностей преобразования текста в SQL (NL2SQL), где естественный язык преобразуется в SQL-запросы, облегчая доступ к данным. Компания Google Cloud получила самую современную оценк…
Telegram ИИ Дайджест
#ai #news
A new top score: Advancing Text-to-SQL on the BIRD benchmark
cloud.google.com
November 15, 2025 at 7:10 PM
Новый рекорд: Улучшение Text-to-SQL на бенчмарке BIRD
В тексте обсуждается развитие возможностей преобразования текста в SQL (NL2SQL), где естественный язык преобразуется в SQL-запросы, облегчая доступ к данным. Компания Google Cloud получила самую современную оценк…
Telegram ИИ Дайджест
#ai #news
В тексте обсуждается развитие возможностей преобразования текста в SQL (NL2SQL), где естественный язык преобразуется в SQL-запросы, облегчая доступ к данным. Компания Google Cloud получила самую современную оценк…
Telegram ИИ Дайджест
#ai #news
Pei, Xu, Zhao, Hou, Chen, Zhang, Luo, He: Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models https://arxiv.org/abs/2503.17811 https://arxiv.org/pdf/2503.17811 https://arxiv.org/html/2503.17811
March 25, 2025 at 5:56 AM
Pei, Xu, Zhao, Hou, Chen, Zhang, Luo, He: Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models https://arxiv.org/abs/2503.17811 https://arxiv.org/pdf/2503.17811 https://arxiv.org/html/2503.17811
XiYan-SQL Revolutionizes NL2SQL Tasks with State-of-the-Art Framework 🚀📊✨ www.azoai.com/news/2024112... #AI #SQL #NaturalLanguage #MachineLearning #DatabaseInnovation #TextToSQL #DataAnalytics #TechResearch #FutureTech #NL2SQL
XiYan-SQL Revolutionizes NL2SQL Tasks with State-of-the-Art Framework
Researchers at Alibaba Group have developed XiYan-SQL, a cutting-edge framework combining multi-generator strategies and enhanced schema representation to achieve state-of-the-art performance in conve...
www.azoai.com
November 21, 2024 at 1:04 AM
XiYan-SQL Revolutionizes NL2SQL Tasks with State-of-the-Art Framework 🚀📊✨ www.azoai.com/news/2024112... #AI #SQL #NaturalLanguage #MachineLearning #DatabaseInnovation #TextToSQL #DataAnalytics #TechResearch #FutureTech #NL2SQL
scenarios for the NL2SQL task. SQLong generates augmented datasets by extending existing database schemas with additional synthetic CREATE TABLE commands and corresponding data rows, sampled from diverse schemas in the [3/5 of https://arxiv.org/abs/2502.16747v1]
February 25, 2025 at 6:27 AM
scenarios for the NL2SQL task. SQLong generates augmented datasets by extending existing database schemas with additional synthetic CREATE TABLE commands and corresponding data rows, sampled from diverse schemas in the [3/5 of https://arxiv.org/abs/2502.16747v1]
applications. State-of-the-art NL2SQL techniques typically perform translation by retrieving database-specific information, such as the database schema, and invoking a pre-trained large language model (LLM) using the question and retrieved information [2/6 of https://arxiv.org/abs/2505.23039v1]
May 30, 2025 at 5:55 AM
applications. State-of-the-art NL2SQL techniques typically perform translation by retrieving database-specific information, such as the database schema, and invoking a pre-trained large language model (LLM) using the question and retrieved information [2/6 of https://arxiv.org/abs/2505.23039v1]
Shuyang Hou, Haoyue Jiao, Ziqi Liu, Lutong Xie, Guanyu Chen, Shaowen Wu, Xuefeng Guan, Huayi Wu: From NL2SQL to NL2GeoSQL: GeoSQL-Eval for automated evaluation of LLMs on PostGIS queries https://arxiv.org/abs/2509.25264 https://arxiv.org/pdf/2509.25264 https://arxiv.org/html/2509.25264
October 1, 2025 at 6:30 AM
Shuyang Hou, Haoyue Jiao, Ziqi Liu, Lutong Xie, Guanyu Chen, Shaowen Wu, Xuefeng Guan, Huayi Wu: From NL2SQL to NL2GeoSQL: GeoSQL-Eval for automated evaluation of LLMs on PostGIS queries https://arxiv.org/abs/2509.25264 https://arxiv.org/pdf/2509.25264 https://arxiv.org/html/2509.25264
TailorSQL: An NL2SQL System Tailored to Your Query Workload Kapil Vaidya, Jialin Ding, Sebastian Kosak, David Kernert, Chuan Lei, Xiao Qin, Abhinav Tripathy, Ramesh Balan, Balakrishnan Narayanaswamy, Tim Kraska https:// arxiv.org/abs/2505.23039 https:/...
| Details | Interest | Feed |
| Details | Interest | Feed |
Origin
mastoxiv.page
May 30, 2025 at 7:25 AM
I don't think "ad hoc" is solvable with LLMs. I think its more about "using SQL as a common language to communicate from the biz to analysts/scientists to data engineers to sw engineers".
We should be able to get much better requirements from the biz with a good NL2SQL interface
We should be able to get much better requirements from the biz with a good NL2SQL interface
November 11, 2024 at 9:54 PM
I don't think "ad hoc" is solvable with LLMs. I think its more about "using SQL as a common language to communicate from the biz to analysts/scientists to data engineers to sw engineers".
We should be able to get much better requirements from the biz with a good NL2SQL interface
We should be able to get much better requirements from the biz with a good NL2SQL interface
Reading: NL2SQL with LangChain and #Azure SQL Database - https://buff.ly/4bLTQwo
#AzureData #AzureSQL
#AzureData #AzureSQL
NL2SQL with LangChain and Azure SQL Database - Azure SQL ...
NL2SQL with LangChain and Azure SQL Database - Learn how ...
buff.ly
November 21, 2024 at 5:13 PM
Reading: NL2SQL with LangChain and #Azure SQL Database - https://buff.ly/4bLTQwo
#AzureData #AzureSQL
#AzureData #AzureSQL
Shubham Mohole, Sainyam Galhotra: VeriMinder: Mitigating Analytical Vulnerabilities in NL2SQL https://arxiv.org/abs/2507.17896 https://arxiv.org/pdf/2507.17896 https://arxiv.org/html/2507.17896
July 25, 2025 at 6:29 AM
Shubham Mohole, Sainyam Galhotra: VeriMinder: Mitigating Analytical Vulnerabilities in NL2SQL https://arxiv.org/abs/2507.17896 https://arxiv.org/pdf/2507.17896 https://arxiv.org/html/2507.17896