Back to papers
July 9, 2026cs.AIcs.CL

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning

Lu Dai, Ziyang Rao, Yili Wang, Hanqing Wang, Hao Liu, Hui Xiong
Read on arXivDownload PDF
HF Upvotes

11

Categories

cs.AI, cs.CL