Interesting research. Down the line it could help better fine tune models and side step some of the attention system limitations. Of course it comes with its own downsides, more research is necessary.

This is one of the handful of uses where I'd expect LLMs to shine. It's nice to see some tooling to make it easier.

Looks like a good resource if you're interested in natural language processing.

Indeed there are a few trends at play right now which lead to RSS being in use again. I can only hope it'll keep growing.