top | item 45719035

(no title)

luke-stanley | 4 months ago

Summarisation models that do not follow instructions already exist! Fixing exfiltration is good, low hanging fruit. But for a summarisation task, whole classes of typical instruction following behaviour are totally off target!

discuss

order

simonw|4 months ago

Which models do you recommend for that these days?

Has the field moved on much since the pre-LLM-era models like T5?