Zhengyang Shan
@shanzzyy.bsky.social
📤 5
📥 3
📝 13
PhD @ Boston University | Researching interpretability & evaluation in large language models
reposted by
Zhengyang Shan
Micah Benson
about 1 month ago
🧠🤖 The 2026 New England Mechanistic Interpretability (NEMI) Workshop will be Aug. 14 at Boston University! Help spread the word and join the New England mech interp community! Registration and submission info in thread:👇
1
7
4
Can steering remove LLM shortcuts without breaking legitimate LLM capabilities? In our
@eaclmeeting.bsky.social
paper, we show that conceptual bias is separable from concept detection; this means inference-time debiasing is possible with minimal capability loss.
6 months ago
6
3
1
you reached the end!!
feeds!
log in
