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
updated a dataset 1 day ago
Jazhyc/gleipnir-kimi-k3-tool-trajectory-logits published a dataset 1 day ago
Jazhyc/gleipnir-kimi-k3-tool-trajectory-logits updated a dataset 3 days ago
Jazhyc/aims-safety-intentsOrganizations
None yet