A country-grounded cross-cultural benchmark for LLM safety and cultural sensitivity across 10 country-language pairs.
AI & ML interests
AI Safety & AI Security
Papers
NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Control Rooms
EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards
Team members 27 private
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 • 130 • 12 -
AIM-Intelligence/COMPASS-Policy-aware-SFT-Dataset
Viewer • Updated • 4.12k • 35 • 2 -
AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA
Text Generation • 8B • Updated • 16 • 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 • 130 • 12 -
AIM-Intelligence/COMPASS-Policy-aware-SFT-Dataset
Viewer • Updated • 4.12k • 35 • 2 -
AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA
Text Generation • 8B • Updated • 16 • 2
Fine-tuned Model Collections using the "Representation Bending" (REPBEND) approach described in Representation Bending for Large Language Model Safety