HoangCuongNguyen/qwen3-8b-safetyorpo
Text Generation • 8B • Updated • 82
🤝 Open to Collab
Hoang Cuong Nguyen
HoangCuongNguyen
AI & ML interests
Natural Language Processing in Cybersecurity/ Safety Alignment for LLMs
Recent Activity
authored a paper 24 days ago
Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness published a dataset 24 days ago
HoangCuongNguyen/refusal-direction-results updated a collection about 1 month ago
EMNLP 2026 Post-Training AnalysisOrganizations
None yet
HoangCuongNguyen/qwen3-8b-safety-ra-sft
Text Generation • 8B • Updated • 83
HoangCuongNguyen/qwen3-8b-safetysft
Text Generation • 8B • Updated • 88
HoangCuongNguyen/gemma-2-9b-safety-ra-sft
Text Generation • 9B • Updated • 53
HoangCuongNguyen/gemma-2-9b-safetysft
Text Generation • 9B • Updated • 71
HoangCuongNguyen/llama-3.1-8b-safety-ra-sft
Text Generation • 8B • Updated • 16
HoangCuongNguyen/gemma-2-9b-safetyorpo
Text Generation • 9B • Updated • 21
HoangCuongNguyen/llama-3.1-8b-safetyorpo
Text Generation • 8B • Updated • 16
HoangCuongNguyen/llama-3.1-8b-safetysft
Text Generation • 8B • Updated • 30
HoangCuongNguyen/Flan-T5-finetuned-cti2
Text Generation • Updated • 17
HoangCuongNguyen/falcon-rw-1b-cti-finetuned
Text Generation • Updated • 18
HoangCuongNguyen/flan-t5-cti-fine-tuned
Updated • 7
HoangCuongNguyen/t5-cti-fine-tuned
Updated • 8
HoangCuongNguyen/llama-2-7b-CTI-research
Text Generation • Updated • 3