A country-grounded cross-cultural benchmark for LLM safety and cultural sensitivity across 10 country-language pairs.
AI & ML interests
AI Safety & AI Security
Recent Activity
View all activity
Papers
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
Organization Card
AIM Intelligence
Securing the Future of AI.
AIM Intelligence is a leading AI safety & security startup dedicated to building safe, reliable, and trustworthy AI . We specialize in automated red teaming and robust defense mechanisms against attacks.
🔗 Connect with Us
- Website: aim-intelligence.com
- LinkedIn: AIM Intelligence
- Contact: team@aim-intelligence.com
A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
-
COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
Paper • 2601.01836 • Published • 10 -
AIM-Intelligence/COMPASS-Policy-Alignment-Testbed-Dataset
Viewer • Updated • 5.92k • 117 • 11 -
AIM-Intelligence/COMPASS-Policy-aware-SFT-Dataset
Viewer • Updated • 4.12k • 30 • 2 -
AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA
Text Generation • 8B • Updated • 5 • 2
A country-grounded cross-cultural benchmark for LLM safety and cultural sensitivity across 10 country-language pairs.
A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
-
COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
Paper • 2601.01836 • Published • 10 -
AIM-Intelligence/COMPASS-Policy-Alignment-Testbed-Dataset
Viewer • Updated • 5.92k • 117 • 11 -
AIM-Intelligence/COMPASS-Policy-aware-SFT-Dataset
Viewer • Updated • 4.12k • 30 • 2 -
AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA
Text Generation • 8B • Updated • 5 • 2
models 9
AIM-Intelligence/Guardian-v0.2-PII-NER-lora-v4
Updated
AIM-Intelligence/Guardian-v0.2-PII-extract-lora-v1
Updated
AIM-Intelligence/Guardian-v0.2-PII-name-address-lora-v3
Updated
AIM-Intelligence/COMPASS_gemma-3-4b-it_LoRA
4B • Updated • 4 • 2
AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA
Text Generation • 8B • Updated • 5 • 2
AIM-Intelligence/RepBend_Llama3_8B
Updated • 3
AIM-Intelligence/RepBend_Mistral_7B
Updated • 1
AIM-Intelligence/RepBend_Llama3_8B_LoRA
Updated • 1
AIM-Intelligence/RepBend_Mistral_7B_LoRA
Updated • 1
datasets 6
AIM-Intelligence/guardian-pii-train-data
Preview • Updated • 155
AIM-Intelligence/EgoSafetyBench
Updated • 26
AIM-Intelligence/XL-SafetyBench
Viewer • Updated • 5.5k • 488 • 6
AIM-Intelligence/fluid-reasoning-representation-phase1
Updated • 32
AIM-Intelligence/COMPASS-Policy-aware-SFT-Dataset
Viewer • Updated • 4.12k • 30 • 2
AIM-Intelligence/COMPASS-Policy-Alignment-Testbed-Dataset
Viewer • Updated • 5.92k • 117 • 11