Wendy K. Tam

Identifiers

• name variant Wendy K. Tam 0.60 · backfill

Papers (2)

1. The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model cs.CL · 2026 · author #1
2. The Amplifying Mirror: Locating and Steering the Partisan Direction inside a Large Language Model cs.CL · 2026 · author #1

Mentions

• 2606.09735 #1 · arxiv_oai · confidence 0.70 Wendy K. Tam
• 2606.08792 #1 · arxiv_oai · confidence 0.70 Wendy K. Tam