Naihao Deng

dnaihao's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 2 datasets about 9 hours ago

MichiganNLP/misfired-alignment

Viewer • Updated about 9 hours ago • 4.06k • 1

MichiganNLP/misfired-alignment-eval-results

Updated about 9 hours ago • 1

published 2 datasets 1 day ago

MichiganNLP/misfired-alignment-eval-results

Updated about 9 hours ago • 1

MichiganNLP/misfired-alignment

Viewer • Updated about 9 hours ago • 4.06k • 1

updated 4 models 6 days ago

MichiganNLP/Qwen2.5-7B-Instruct-bias-z12-Age-lora

Updated 6 days ago

MichiganNLP/Llama-3.1-8B-Instruct-bias-z12-Age-lora

Updated 6 days ago

MichiganNLP/Qwen2.5-3B-Instruct-bias-z12-Age

3B • Updated 6 days ago • 446

MichiganNLP/Llama-3.2-3B-Instruct-bias-z12-Age

4B • Updated 6 days ago • 110

updated a collection 6 days ago

One-Shot GRPO Bias

Collection

Bias-collapsed models + flipped-label data from 'It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO'. Gated, research-only. • 11 items • Updated 6 days ago

updated a model 7 days ago

MichiganNLP/Llama-3.2-3B-Instruct-bias-z100-Disability

4B • Updated 6 days ago • 121

published a model 7 days ago

MichiganNLP/Llama-3.2-3B-Instruct-bias-z100-Disability

4B • Updated 6 days ago • 121

updated a model 7 days ago

MichiganNLP/Llama-3.2-3B-Instruct-bias-z87-Disability

4B • Updated 6 days ago • 42

published a model 7 days ago

MichiganNLP/Llama-3.2-3B-Instruct-bias-z87-Disability

4B • Updated 6 days ago • 42