Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
MAUVEkrishnap25.github.ioMAUVE is a library built on PyTorch and HuggingFace Transformers that measures the gap between neural text and human text using Kullback–Leibler divergences in a quantized embedding space. It correlates strongly with human evaluations for open-ended text generation and can be applied to other modalities like images or speech with appropriate embeddings.
Parse Score
Sources
en.wikipedia.org shapes more of what AI says about MAUVE than any other source, at 100% of its citations.
