作者位次 #2/10ACL 2026Poster· Natural Language Processing
Multi-Granularity Semantic Revision for Large Language Model Distillation
Xiaoyu Liu · Yun Zhang · Wei Li · Simiao Li · XUDONG HUANG · Hanting Chen · Yehui Tang · Jie Hu · Zhiwei Xiong · Yunhe Wang
摘要
Knowledge distillation is crucial for compressing Large Language Models (LLMs), enabling smaller student models to learn from larger teacher models. However, existing LLM distillation methods overly rely on student-generated outputs, which may introduce generation errors and misguide the distilla...