Following Length Constraints in Instructions
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
presents an approach for how to deal with length bias and train instruction following language models that better follow length constraint instructions; fine-tunes a model using DPO with a length instruction augmented dataset and shows less length constraint violations and while keeping a high response quality.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack