ydeng9 (Yihe Deng)

reacted to their post with ❤️ over 1 year ago

Post

1690

Check out our new benchmark paper on LLM agents for global events forecasting! MIRAI: Evaluating LLM Agents for Event Forecasting (2407.01231)

📜 Arxiv: https://arxiv.org/abs/2407.01231
🔗 Project page: https://mirai-llm.github.io
💻 GitHub Repo: https://github.com/yecchen/MIRAI
📁 Dataset: https://drive.google.com/file/d/1xmSEHZ_wqtBu1AwLpJ8wCDYmT-jRpfrN/view?usp=sharing
📊 Interactive Demo Notebook: https://colab.research.google.com/drive/1QyqT35n6NbtPaNtqQ6A7ILG_GMeRgdnO?usp=sharing

posted an update over 1 year ago

Post

1690

Check out our new benchmark paper on LLM agents for global events forecasting! MIRAI: Evaluating LLM Agents for Event Forecasting (2407.01231)

📜 Arxiv: https://arxiv.org/abs/2407.01231
🔗 Project page: https://mirai-llm.github.io
💻 GitHub Repo: https://github.com/yecchen/MIRAI
📁 Dataset: https://drive.google.com/file/d/1xmSEHZ_wqtBu1AwLpJ8wCDYmT-jRpfrN/view?usp=sharing
📊 Interactive Demo Notebook: https://colab.research.google.com/drive/1QyqT35n6NbtPaNtqQ6A7ILG_GMeRgdnO?usp=sharing

reacted to banghua's post with 👍 almost 2 years ago

Post

🚀 Exciting breakthrough in LLM reliability! 🧠NexusRaven-V2, our cutting-edge function-calling LLM, has set a new standard in minimizing AI hallucinations, surpassing GPT-4's performance in a recent third-party independent research benchmark.

Dive into our latest blog post to explore how we're pioneering reliable agents with minimal hallucinations: https://nexusflow.ai/blogs/towards-reliable-agents-with-minimal-hallucination

Key Highlights:

🏆 Zero Hallucinations: NexusRaven-V2 showcased remarkable accuracy with zero hallucinations in 840 tests, focusing on tool selection and usage – a significant leap over GPT-4 with 23 hallucinations.

📈 Enhanced Success Rates: It boasts a 9% higher success rate than GPT-4 in information-seeking applications requiring meticulous attention to detail and a 4% increase in adversarial scenarios that demand a deep understanding of tool documentation, even with vague tool and API argument names.

Try NexusRaven-V2 on Huggingface: Nexusflow/NexusRaven-V2-13B

Check out the original third-party benchmark: https://arxiv.org/abs/2401.08326

Yihe Deng PRO

AI & ML interests

Recent Activity

Organizations

Yihe Deng PRO

AI & ML interests

Recent Activity

Organizations

ydeng9's activity