作者位次 #2/4ACL 2026Findings· Findings of ACL
Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Large Language Models through Latent Semantic Alignment
Jian Gu · Aldeida Aleti · Chunyang Chen · Hongyu Zhang
摘要
Large Language Models (LLMs) encode substantial knowledge in their parameters, which can be located, traced, and analyzed. Despite recent progress in neural interpretability, it is still unclear how to transfer such knowledge in a fine-grained manner, namely parametric knowledge transfer (PKT). A...