Hacker News Reader

> 7B parameter Orca-2.5 model aligned by DNO achieves the state-of-the-art win-rate against GPT-4-Turbo of 33% on AlpacaEval 2.0 (even after controlling for response length), an absolute gain of 26% (7%→33%) over the initializing model. It outperforms models with far more parameters, including Mistral Large, Self-Rewarding LM (70B parameters), and older versions of GPT-4

edit: updated quote w/ more context

View on HN

Still only 33% though. Which is impressive for a 7B model, but the student has not yet surpassed the teacher

If you only emulate the teacher can you ever become an master?

It works in many competitive fields

Surely it needs more than just emulating the teacher, though, it would require exploring beyond those limitations?

But eventually your human mentor diminishes with age.

And then you can crush them.

author here; yea the goal is to try and get the student to surpass the teacher, but if it can't, this is the best way to get close. For these contrastive losses, our intuition is that the model isn't trying to emulate the teacher so much as learning from the 'delta' between itself and the teacher

Reply on news.ycombinator.com