arxiv
PublishedMay 22, 2026 at 4:00 AM
—neutral
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection
Publisher summary· verbatim
arXiv:2605.16865v2 Announce Type: replace Abstract: Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasoning and general-domain performance. We argue this forgetting arises because fine-tuning targets fr
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivEDEN: A Large-Scale Corpus of Clinical Notes for Italian22harxivASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection22harxivLoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling22harxivProjected random forests and conformal prediction of circular data22hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗