Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
Paper • 2605.27355 • Published • 2
Dongyoon Hahm
Hahmdong
AI & ML interests
AI Safety
Recent Activity
updated a model 26 minutes ago
Hahmdong/RMOOD-qwen3-4b-it-skywork-bias-analysis-markdown-p10-p100 published a model 30 minutes ago
Hahmdong/RMOOD-qwen3-4b-it-skywork-bias-analysis-markdown-p10-p100Organizations
None yet