iiinova — where your digital self keeps evolving

Zhengyang Shan

@shanzzyy.bsky.social

5 followers 3 following 13 posts

PhD @ Boston University | Researching interpretability & evaluation in large language models

Posts Replies Media

Reposted by Zhengyang Shan

Micah Benson @micahben.bsky.social · 10/06/2026

🧠🤖 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:👇

1102

Zhengyang Shan @shanzzyy.bsky.social · 20/01/2026

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.

630