Good question. In their original finetuning, they train a reward model based on relative preference (rankings among multiple responses). And from the user feedback, there's only thumbs up & down. You can probably use that for supervised finetuning I guess.
RESEARCH
-
Reasons Behind OpenAI Models’ Superior Performance Remain Unknown
By
–
Yeah. And we still don't know why OpenAI models are better: 1. More and better data?
2. Larger pretrained base model?
3. RLHF instead of supervised finetuning? My guess is it's probably all of these above. -
Dataset Importance for LLM Fine-tuning: Camels Paper Insights
By
–
And the recent "How Far Can Camels Go" paper (
https://
arxiv.org/abs/2306.04751) is a nice example of how important the dataset for LLM finetuning is. -
LLM Enhanced with Search and Symbolic Math Tools
By
–
The important part is when the LLM will be combined with search and symbolic math tool – the latter will enhance logical reasoning.
-
AI Industry Leaders Issue Extinction Risk Warning Statement
By
–
#AI industry and researchers sign statement warning of ‘extinction’ risk https://
cnn.it/3C0kqBB #ethics #FutureofWork -
8 Best Statistics Books to Empower Your AI Journey
By
–
Unlock the Power of Numbers! On the occasion of National Statistics Day, we present the 8 Best Statistic Books to ignite the minds of AI enthusiasts. Embark on a knowledge-packed journey to empower your AI endeavours!
Read more about these books: https://
rb.gy/8hk0v -
Bytes Bias: Unraveling the Myth of Neutral AI
By
–
When Bytes Bias: Unraveling the Myth of Neutral AI https://
x.com/i/broadcasts/1
MYxNgnZrrNKw
… -
OpenFlamingo v2: Enhanced Multimodal AI Model Released
By
–
Our friends @anas_awadalla (U of Washington) and @irena_gao (Stanford) released this cool project with our compute support: OpenFlamingo v2: New Models and Enhanced Training Setup. Pls check it out on our AI blog and provide feedback!
-
Bias in AI: Exploring Myths of Neutral Artificial Intelligence
By
–
Join me TODAY for an insightful livestream on "When Bytes Bias: Unraveling the Myth of Neutral AI"! 12 Noon UK | ET 7AM | PT 4AM | CET 1PM | SGT 7PM Twitter > https://
lnkd.in/ehrXiUW #AIethics #BiasInTech #NeutralAI #Livestream #MeredithBroussard #AI #JoinTheDiscussion -
Synthetic Biology Advancements Will Transform Society Within Decade
By
–
The coming wave really is coming, like it or not. Advanced synthetic biology (for enhancements or otherwise)will be widely available in a decade https://t.co/cCX2sYTtE3
— Mustafa Suleyman (@mustafasuleyman) 29 juin 2023The coming wave really is coming, like it or not. Advanced synthetic biology (for enhancements or otherwise)will be widely available in a decade