A benchmark and evaluation of Qwen3.5-4B focused on uncertainty, hallucination, and knowledge boundaries across languages, prompt framings, and intera
Muhammad Ahmad
mahmad1882
AI & ML interests
None yet
Recent Activity
updated a bucket 5 days ago
mahmad1882/blind-spots published a bucket 5 days ago
mahmad1882/blind-spots updated a collection 6 days ago
Blinds Spots of Frontier Models (FF 2026)Organizations
None yet