demonstrations

Tag

Cards List
#demonstrations

When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning

arXiv cs.LG · 2026-05-27 Cached

This paper reveals a counterintuitive phenomenon where correct demonstrations in in-context learning can degrade model accuracy, introducing task preserving perturbations to study the gap between exemplar correctness and utility.

0 favorites 0 likes
#demonstrations

Self-Distillation Enables Continual Learning [pdf]

Hacker News Top · 2026-05-17 Cached

Introduces Self-Distillation Fine-Tuning (SDFT), a method that enables on-policy learning from demonstrations to achieve continual learning without catastrophic forgetting, outperforming supervised fine-tuning.

0 favorites 0 likes
← Back to home

Submit Feedback