From the source
Larger models are better at self-critiquing, and scaling improves critique-writing more than summary-writing.
AI-written critiques help humans notice flaws
OpenAI trained critique-writing models that help humans notice flaws in summaries.
Story of the weekResearch paper
From the source
We trained “critique-writing” models to describe flaws in summaries. Human evaluators find flaws in summaries much more often when shown our model’s critiques. Larger models are better at self-critiquing, with scale improving critique-writing more than summary-writing.
openai.com
