Scholar
Bruce W. Lee
Google Scholar ID: a9HZkjMAAAAJ
University of Pennsylvania
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
316
H-index
9
i10-index
9
Publications
18
Co-authors
0
Publications
7 items
Alignment Forecasting: Predicting Misalignment From Training Data
2026
Cited
0
Reasoning Models Struggle to Control their Chains of Thought
2026
Cited
0
Training Agents to Self-Report Misbehavior
2026
Cited
0
Distillation Robustifies Unlearning
2025
Cited
0
Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
2025
Cited
0
Programming Refusal with Conditional Activation Steering
arXiv.org · 2024
Cited
5
When Prompting Fails to Sway: Inertia in Moral and Value Judgments of Large Language Models
2024
Cited
1
