Postări cu #Text2sql
#Text2sql
Postări publice de pe X care folosesc #Text2sql.
Hashtaguri înrudite
Tanmay Parekh@tparekh97Proposing a new “Parallel Exploration” Agentic framework PExA for complex code generation, specifically text-to-SQL. We achieve one of the best numbers on the Spider 2.0 leaderboard. Paper incoming on ArXiv soon! #agenticAI #text2sql #llmTech At Bloomberg @TechAtBloombergA team of researchers from Bloomberg’s #AI Engineering group introduced PExA, an #agenticAI framework that achieved 70.2% execution accuracy on the Spider 2.0 leaderboard, one of the most demanding benchmarks for #text2sql generation #CodeGeneration (1/2)2191.2K
Tech At Bloomberg@TechAtBloombergA team of researchers from Bloomberg’s #AI Engineering group introduced PExA, an #agenticAI framework that achieved 70.2% execution accuracy on the Spider 2.0 leaderboard, one of the most demanding benchmarks for #text2sql generation #CodeGeneration (1/2)1091.8K- #QueryWeaver #MCP is out! Talk with your database(s) with this open-source #Text2SQL tool 👇 Check it out: See it in action today (9.9):013278
Excited to share that our recent work DivSkill-SQL is now ranked #1 on the official Spider2-Lite leaderboard🎉 Text-to-SQL agent ensembling, which generates multiple SQL candidates, then selects the best one, has been shown to be effective.
15141.5K- @J10ngl1ZOur idea is to optimize the ensemble more directly for Pass@K. Specifically, we aim to learn residual skills that capture the missing capabilities needed to address what existing agents fail to solve. This leads to more diverse, targeted, and effective Text-to-SQL ensembles.103176
- @J10ngl1ZHuge thanks to collaborators at Snowflake AI Research and UCSD: @howardghqqq, @parjanyapp, @nikkiklj1, @BaharanKhatami, @XuCanwen, @Xiaodong_Yu_126, @YingyuL2, @yao_zhewei, @YuxiongH, Babak Salimi! Our paper: #Text2SQL #Agents #LLM #Databases103266
Thank you @AstronomerAmber and @arizeai for having me on the paper reading podcast to discuss my PhD work about #text2sql and #LLMs. It was really fun! The recording is available now atArize AI @arizeaiTomorrow we're joined by @ShuaichenChang who will discuss his research on the impact of prompt constructions on #LLM performance with @AstronomerAmber. Register here:1382.1K
Arize AI@arizeaiTomorrow we're joined by @ShuaichenChang who will discuss his research on the impact of prompt constructions on #LLM performance with @AstronomerAmber. Register here:
1012.3K
Turing@turingcomUnlock the power of synthetic data!💡 Explore our latest proof-of-concept study at Turing, showcasing how we’re transforming natural language into SQL queries with precision. 🚀 Read the full blog here: #AI #SyntheticData #Text2SQL #Innovation013334
MyScale@MyScaleDB🥳Introducing an excellent update on ChatData! Wikipedia is now available as a knowledge base! 😉Come unlock the true potential of information retrieval with ChatData and discover a world of knowledge at your fingertips. #selfquery #text2sql #vectorsql #vectordatabase0296K
The Yuan Community@YuanCommunityAs #data-driven organizations look for the best ways to power their businesses and remain competitive, this article seeks to help them do so by providing a guide to implementing conversational access to enterprise data using #Text2SQL. @TDataScience002949
Davood Rafiei@DavoodRafieiOur #EMNLP2023 main paper "Evaluating Cross-Domain Text-to-SQL Models and Benchmarks" is now at The evaluation includes major #text2sql benchmarks, showing some of the areas for improvement. #spider #bird107364
Simone Balloccu@simoneballoccu🚨Happy to share that our paper "Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs" has been accepted at #eacl2024.🚨 Huge thanks to my co-authors @PSchmidtova, @LangoMateusz and @tuetschek. Link:
3217819.7K
Fede_Ranaldi@FedeRanaldi@simoneballoccu@simoneballoccu @PSchmidtova @LangoMateusz @tuetschek Very considerable work! DC is an intriguing problem not only for evaluation but also witnesses the ambiguity between learning and memorization. You'll probably find interesting our work that is deeply dedicated to Text-to-SQL. #datacontamination #text2sql00383
Visper.io@VisperIo4156🚫 "Text2SQL" is too narrow — data is more than queries. ✨ With Visper, your whole team can go from questions → insights → dashboards in one flow. Why Visper is a leap beyond Text2SQL 👇 🔗 #text2sql #DataAnalytics #AI01241
Albert Villanova@avillanovamoralReally interesting article by @andrejanysa about #text2sql using @huggingface datasets viewer and @duckdb014344- Davood Rafiei@DavoodRafieiOur paper on "Evaluating Cross-Domain Text-to-SQL Models and Benchmarks" is accepted to EMNLP 2023. The evaluation includes #spider and #bird. Congrats to M. Pourreza for the great work. It is coming to arXiv soon. #text2sql206700
Our latest blog 📖 discusses the latest innovations in TiDB Cloud ☁️ including #Text2SQL. Learn about the improvements to Chat2Query that make data interactions easier and more efficient. 🌐 Read the blog, and try Chat2Query for free today! #Chat2Query
003416
- Arată mai multe postări
