{"type":"link","version":"1.0","title":"Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks","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/arxiv2205.05718","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2205.05718.png","thumbnail_width":1200,"thumbnail_height":630}