Human-AI hybrids achieve only +0.4pp over AI alone on diverse tasks because confidence routing fails to identify the small set of cases where humans can correct AI errors.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Chain-of-thought monitorability provides a promising but fragile method for AI safety oversight that developers should actively preserve.
Gemma 2 models achieve leading performance at their sizes by combining established Transformer modifications with knowledge distillation for the 2B and 9B variants.
citing papers explorer
-
Toward Human-AI Complementarity Across Diverse Tasks
Human-AI hybrids achieve only +0.4pp over AI alone on diverse tasks because confidence routing fails to identify the small set of cases where humans can correct AI errors.
-
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Chain-of-thought monitorability provides a promising but fragile method for AI safety oversight that developers should actively preserve.
-
Gemma 2: Improving Open Language Models at a Practical Size
Gemma 2 models achieve leading performance at their sizes by combining established Transformer modifications with knowledge distillation for the 2B and 9B variants.