Hahmdong/RMOOD-llama3.2-3b-it-skywork-doubledatarm-biased150-to-good50
3B • Updated • 17
Dongyoon Hahm
Hahmdong
AI & ML interests
AI Safety
Recent Activity
submitted a paper 1 day ago
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases authored a paper 2 days ago
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned BiasesOrganizations
None yet
Hahmdong/RMOOD-llama3.2-3b-it-skywork-doubledatarm-biased100-to-good100
3B • Updated • 17
Hahmdong/RMOOD-llama3.2-3b-it-skywork-doubledatarm-biased50-to-good150
3B • Updated • 16
Hahmdong/RMOOD-llama3.2-3b-it-skywork-rm-clean
3B • Updated • 17
Hahmdong/RMOOD-llama3.2-3b-it-skywork-rm-clean-length-0.9
3B • Updated • 15
Hahmdong/RMOOD-qwen3-4b-it-skywork-doubledatarm-good50-to-biased150
4B • Updated • 15
Hahmdong/RMOOD-qwen3-4b-it-skywork-doubledatarm-biased150-to-good50
4B • Updated • 14
Hahmdong/RMOOD-qwen3-4b-it-skywork-doubledatarm-biased100-to-good100
4B • Updated • 15
Hahmdong/RMOOD-qwen3-4b-it-skywork-doubledatarm-biased50-to-good150
4B • Updated • 15
Hahmdong/RMOOD-qwen3-4b-it-skywork-rm-clean-length-0.9
4B • Updated • 17
Hahmdong/RMOOD-qwen3-4b-it-skywork-rm-clean
4B • Updated • 14
Hahmdong/RMOOD-qwen3-4b-it-skywork-rm-length-0.8
4B • Updated • 5
Hahmdong/RMOOD-qwen3-4b-it-skywork-rm-length-0.9
4B • Updated • 5
Hahmdong/RMOOD-qwen3-4b-ultrafeedback-gemini-reweight-rm-length-0.9
4B • Updated • 237
Hahmdong/RMOOD-qwen3-4b-ultrafeedback-gemini-rm-length-0.9
4B • Updated • 231
Hahmdong/RMOOD-qwen3-4b-base-skywork-rm-length-0.8
4B • Updated
Hahmdong/RMOOD-qwen3-4b-ultrafeedback-gemini-rm
4B • Updated • 1
Hahmdong/RMOOD-qwen3-4b-ultrafeedback-gemini-rm-length
4B • Updated • 1
Hahmdong/RMOOD-llama3.2-3b-ultrafeedback-gemini-rm-full-unbiased
3B • Updated • 4
Hahmdong/RMOOD-llama3.2-3b-ultrafeedback-gemini-conflictrm-no-warmup-length
3B • Updated • 4
Hahmdong/RMOOD-llama3.2-3b-ultrafeedback-gemini-rm-length
3B • Updated • 1
Hahmdong/RMOOD-llama3.2-3b-ultrafeedback-gemini-conflictrm-coeff-length
3B • Updated • 2
Hahmdong/RMOOD-llama3.2-3b-ultrafeedback-gemini-pcgradrm-length
3B • Updated
Hahmdong/AT-llama3.1-8b-hhrlhf-5120-rm-ai
8B • Updated • 2
Hahmdong/AT-llama3.1-8b-hhrlhf-5120-sft-b3s3-ai
8B • Updated • 6
Hahmdong/AT-llama3.1-8b-hhrlhf-5120-sft-b3-ai
8B • Updated • 4
Hahmdong/AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-44
4B • Updated • 3
Hahmdong/AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-40
4B • Updated • 1
Hahmdong/AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-36
4B • Updated
Hahmdong/AT-qwen3-4b-ultrachat-hhrlhf-15360-rm-ppo-clean-p0_05-step-32
4B • Updated