一作ACL 2026Poster· Natural Language Processing
Protecting Language Models Against Unauthorized Distillation through Trace Rewriting
Xinhang Ma · William Yeoh · Ning Zhang · Yevgeniy Vorobeychik
摘要
Knowledge distillation is a widely adopted technique for transferring capabilities from LLMs to smaller, more efficient student models.However, unauthorized use of knowledge distillation takes unfair advantage of the considerable effort and cost put into developing frontier models.We investigate...