Yili Wang

HKUST(GZ)

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Interpretability & Mechanistic Interp (1)Reasoning & Chain-of-Thought (1)

Frequent co-authors

Lu Dai (1)Ziyang Rao (1)Hanqing Wang (1)Hao Liu (1)

Papers (1)

Jul 9, 2026

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

Memorized knowledge in LLMs can remain dormant due to misalignment in activation routing, but targeted interventions can unlock substantial gains in reasoning performance.

Lu Dai, Ziyang Rao, Yili Wang +3

Interpretability & Mechanistic Interp Reasoning & Chain-of-Thought

Search

Yili Wang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)