Human-annotated intent dataset and intent-aware safety classifiers (SFT, DPO, distillation, GRPO) for robust LLM guardrails.
Jeremias Ferrao
Jazhyc
·
AI & ML interests
None yet
Recent Activity
upvoted a collection 10 days ago
AIMS: Intent-Aware Safety Classification updated a collection 11 days ago
AIMS: Intent-Aware Safety Classification updated a collection 11 days ago
AIMS: Intent-Aware Safety ClassificationOrganizations
None yet
models 7
Jazhyc/Llama-3.1-8B-aims-grpo
Text Generation • 8B • Updated • 26
Jazhyc/Llama-3.1-8B-aims-le-dpo
Text Generation • Updated • 32
Jazhyc/Llama-3.1-8B-aims-distill-synthetic-intent
Text Generation • Updated • 25
Jazhyc/Llama-3.1-8B-aims-sft-generation
Text Generation • Updated • 38
Jazhyc/gemma-3-12b-intent-jailbreak-classifier-sft
Text Generation • Updated • 4
Jazhyc/gemma-3-12b-intent-jailbreak-classifier
Text Generation • Updated • 4
Jazhyc/modernbert-wildguardmix-classifier
Text Classification • 0.1B • Updated • 101 • 2