{"type":"link","version":"1.0","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/arxiv2404.16966","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2404.16966.png","thumbnail_width":1200,"thumbnail_height":630}