Aligning LLMs with Demonstrated Feedback
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
proposes a method to align LLMs to a specific setting via a very small number of demonstrations as feedback; it aligns LLM outputs to a user’s demonstrated behaviors and can learn fine-grained style and task alignment across domains; outperforms few-shot prompting, SFT, and self-play methods on the tested benchmarks.
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