Latest posts

• The art of data development for Enterprise LLMs
  April 16, 2024Snorkel Team
  - Snorkel's Paroma Varma and Google's Ali Arsenjani discus the role of data in the development and implementation of LLMs. ...
• How Snorkel topped the AlpacaEval leaderboard (and why we’re not there anymore)
  April 9, 2024Hoang Tran
  - Snorkel AI placed a model at the top of the AlpacaEval leaderboard. Here's how we built it, and how it changed AlpacaEval's metrics. ...
• CRFM’s HELM and enterprise LLM evaluation beyond accuracy
  April 3, 2024Vivek Krishnamurthy
  - As Snorkel AI prepares to build better enterprise LLM evaluations, we spoke with Yifan Mail from Stanford's CRFM HELM project. ...
• How we achieved 89% accuracy on contract question answering
  April 2, 2024Minhajul Hoque
  - A customer wanted an llm system for complex contract question answering tasks. We helped them build it—beating the baseline by 64 points. ...
• Five sessions not to miss at Google Cloud Next 24
  March 27, 2024Friea Berg
  - Snorkel AI will be at Google Cloud Next. The event will feature more than 700 sessions, so we picked five that we think you shouldn't miss. ...
• Content filtering breakthrough: Snorkel client reaches 96% recall in 3 days
  March 26, 2024Gabe Smith
  - Snorkel AI helped a client solve the challenge of social media content filtering quickly and sustainably. Here's how. ...
• Here’s how Snorkel Flow + Google AI built an enterprise-ready model in a day
  March 19, 2024Dr. Ali Arsanjani (Google) and Paroma Varma (Snorkel AI)
  - Google and Snorkel AI customized PaLM 2 using domain expertise and data development to improve performance by 38 F1 points in a matter of hours. ...
• Snorkel teams with Microsoft to showcase new AI research at NVIDIA GTC
  March 18, 2024Doug Kelly (Microsoft), Friea Berg (Snorkel AI)
  - Microsoft infrastructure facilitates Snorkel AI research experiments, including our recent high rank on the AlpacaEval 2.0 LLM leaderboard. ...