arxiv
PublishedJuly 20, 2026 at 4:00 AM
—neutral
SODA: Semi On-Policy Black-Box Distillation for Large Language Models
Publisher summary· verbatim
arXiv:2604.03873v4 Announce Type: replace-cross Abstract: Black-box knowledge distillation for large language models presents a strict trade-off. Simple off-policy methods (e.g., sequence-level knowledge distillation) struggle to correct the student's inherent errors. Fully on-policy methods (e.g.,
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
arxivADS-C: Antidistillation Sampling for Classification18harxivBeyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes18harxivFrom Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems18harxivA Formally Grounded ODRL Evaluator: Implementation and Comparison18hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗