[verdverm]

Concur, I discovered UMAP when looking for a way to dimension reduce and visualize embeddings, and it also works on non-embedded data too. Interesting idea to think about it applied to arguments in a debate... especially in conjunction with the work around using LLMs to infer knowledge graphs

https://umap-learn.readthedocs.io/en/latest/basic_usage.html

> Uniform Manifold Approximation and Projection (UMAP) is a dimension reduction technique that can be used for visualisation similarly to t-SNE, but also for general non-linear dimension reduction. The algorithm is founded on three assumptions about the data

1. The data is uniformly distributed on Riemannian manifold;

2. The Riemannian metric is locally constant (or can be approximated as such);

3. The manifold is locally connected.