Dialect-aware LLM safety classifiers from the DIA-GUARD project — fine-tuned on 48 English dialects for safe/unsafe content detection.
Jason Lucas
jsl5710
·
AI & ML interests
Trustworthy AI, Multilingual NLP, Low-Resource Languages, Safe AI, Transfer Learning, AI for Cybersecurity, Human-Center AI, Privacy and Security
Recent Activity
updated a model 1 day ago
jsl5710/Shield-Qwen3-4B-SafeRL-FT-PEFT-CE published a model 1 day ago
jsl5710/Shield-Qwen3-4B-SafeRL-FT-PEFT-CE updated a model 2 days ago
jsl5710/Shield-Qwen3.5-0.8B-Full-FT-CEOrganizations
