Türkçe

#Text2sql içeren gönderiler

#Text2sql

X'te #Text2sql kullanan herkese açık gönderiler.

İlgili etiketler

  1. winner✓@danny0dong
    LLM生成的SQL修不好，别只把报错再喂回去。 一项覆盖3000多条样本、3种SQL方言的实验，用静态属性检查约束修复：解决了传统报错反馈仍未修好的77.8%执行错误，Token少用30%。不过这只是实验结果，实际情况仍然要验证的。 #Text2SQL #SQL修复 #Agent评测
    10242
  2. Łukasz Borchmann✓@LukaszBorchmann
    Is complex reward engineering essential for state-of-the-art text-to-SQL? We've just released Arctic-Text2SQL-R1, which answers this question "NO." See 🧵 and #Text2SQL #LLM
    İndir
    155321.7K
  4. Jiongli Zhu✓@J10ngl1Z
    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.
    İndir
    15141.5K
  5. Jiongli Zhu✓@J10ngl1Z
    @J10ngl1Z
    Our 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
  8. ハカセ アイ(Ai-Hakase)🐾生成AI・ComfyUI✓@ai_hakase_
    【4Bの小型AIが巨大モデルを凌駕！】 爆速のText2SQLモデルが登場！4BながらDeepSeek-V3に匹敵する精度を誇り、MacBookでも2秒以内に回答可能です。ローカル環境で安全・高速にデータ分析を自動化できますね！✨ #AI #Text2SQL
    İndir
    113441
  9. Tanmay Parekh@tparekh97
    Proposing 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 #llm
    Tech At Bloomberg @TechAtBloomberg
    A 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
  10. Tech At Bloomberg@TechAtBloomberg
    A 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
  11. Wren AI✓@getwrenai
    Wren AI Open-Source SQL AI Agent. Text2SQL Made Easy! See how easy it is to query your database without writing SQL. Just ask questions to Wren AI. GitHub: Website: #text2sql #sql #dbgpt #gpt #openai #ollama #ai
    İndir
    038921
  12. Prem✓@premai_io
    Text to SQL is a class of problems when solved introduces amazing usecases like LLM assisted data analysis or any kind of #RAG based use case whose data sources are databases instead of documents. This 🧵 discusses how much #Text2SQL is a solved problem.
    İndir
    127589
  14. Zcode AI Sports Picks✓@ZcodeAI
    An indispensable neural network for #SQL queries. #Text2sql will easily turn your text into a ready-made query. And if you don't understand what's going on in the request, just drop it in a special section and the program will explain it in detail. #Crypto #ai #Bitcoin
    İndir
    204517
  15. 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 #vectordatabase
    İndir
    0296K
  16. Steve.Shi@database_llm
    A very nice survey of alignment research, we are considering aligning llm generated sqls with its execution cost. #llms #text2sql #SQL
    elvis @omarsar0
    If you are interested in reviewing research on alignment for LLMs, look no further. This new survey paper covers different aspects of alignment research such as data collection, training methodologies, and model evaluation. Aligning LLMs with human expectations is an active area of research but is already responsible for some of the most advanced LLMs we have today. This paper sheds light on this area of research, tactics, and insights, including challenges and future directions. It's an impressive resource for researchers and practitioners. There is also a nice GitHub repo along with the paper. paper: repo:
    022335
  17. elvis✓@omarsar0
    If you are interested in reviewing research on alignment for LLMs, look no further. This new survey paper covers different aspects of alignment research such as data collection, training methodologies, and model evaluation. Aligning LLMs with human expectations is an active area of research but is already responsible for some of the most advanced LLMs we have today. This paper sheds light on this area of research, tactics, and insights, including challenges and future directions. It's an impressive resource for researchers and practitioners. There is also a nice GitHub repo along with the paper. paper: repo:
    İndir
    6240901122K
  19. Davood Rafiei@DavoodRafiei
    Our 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. #text2sql
    206700
  22. Davood Rafiei@DavoodRafiei
    Our #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 #bird
    107364
  23. OSS Insight✓@OSSInsight
    It's easy to generate a 2022 summary of a #GitHub repository with #OpenAI: 1. Open (or choose another repo) 2. Ask questions with natural language 3. Run SQL (generated by AI) to get result Q1: How many pull requests open in 2022 of this repo #OpenSource
    İndir
    34133.2K
  25. Daha fazla gönderi göster