tgoop.com/awesomedeeplearning/228
Create:
Last Update:
Last Update:
Finally, we have a hallucination leaderboard! ππ
Key Takeaways
π Not surprisingly, GPT-4 is the lowest.
π Open source LLama 2 70 is pretty competitive!
π Google's models are the lowest. Again, this is not surprising given that the #1 reason Bard is not usable is its high hallucination rate.
Really cool that we are beginning to do these evaluations and capture them in leaderboards!
BY GenAi, Deep Learning and Computer Vision

Share with your friend now:
tgoop.com/awesomedeeplearning/228