AINeutralarXiv – CS AI · 8h ago6/10
🧠
Uncovering Competency Gaps in Large Language Models and Their Benchmarks
Researchers propose a new method using sparse autoencoders to automatically identify competency gaps in large language models, uncovering both specific model weaknesses and imbalances in benchmark design. The approach validates previously documented gaps like sycophancy while discovering novel limitations, offering developers a tool to improve LLM evaluation and benchmark construction.