Considering the very small difference between just SFT on the student model as compared to SFT + DPO on a proxy, doesn't it make sense to concentrate on ensuring the SFT dataset is perfect rather than sorry about DPO etc? And just train directly on the student model?
“Relevant to anyone building failure-attribution systems for agent pipelines — black-box distillation techniques here could feed into causal attribution models without needing white-box access to the underlying model.”
The Chinese are really going strong on destroying the American AI economy bubble. Honestly, despite the fact that I'm totally pro USA and anti China, I think we should help them crashing the American AI bubble. They are controlling everything and we can't even buy a new computer nowadays while getting no benefit from this. I wish some influential programmers stimulated coders everywhere to skip Claude and Chatgpt subscriptions for Chinese ones, at scale. If we programmers united we could help this bubble burst, I'm sure.
Considering the very small difference between just SFT on the student model as compared to SFT + DPO on a proxy, doesn't it make sense to concentrate on ensuring the SFT dataset is perfect rather than sorry about DPO etc? And just train directly on the student model?
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
Related paper that's a good read: https://arxiv.org/abs/1908.08962
Why is this published again? Is this a reference to recent events?
I just saw some post about it on Threads and found it interesting so decided to share!
My best guess is this is a reference to the recent accusations from Anthropic of chinese labs ¨distilling¨ on their models
And it’s a paper from Alibaba researchers, the company/lab that Anthropic called out by name.
“Relevant to anyone building failure-attribution systems for agent pipelines — black-box distillation techniques here could feed into causal attribution models without needing white-box access to the underlying model.”
The Chinese are really going strong on destroying the American AI economy bubble. Honestly, despite the fact that I'm totally pro USA and anti China, I think we should help them crashing the American AI bubble. They are controlling everything and we can't even buy a new computer nowadays while getting no benefit from this. I wish some influential programmers stimulated coders everywhere to skip Claude and Chatgpt subscriptions for Chinese ones, at scale. If we programmers united we could help this bubble burst, I'm sure.
The US government will do the job of destroying the American AI economy through their export controls.
The US "product machine" is so strong. They really know how to do frictionless signup and vendor lock-in on the corporate side.
> skip Claude and Chatgpt subscriptions for Chinese ones, at scale. If we programmers united we could help this bubble burst, I'm sure.
I'm doing my part!
Can we note that this is a 2024 paper in the title?
test comment from modgate