>It does not affect writing quality at all, provably
Prove it, then? It's not a claim that GumbelSoft paper makes: "Regarding generation quality (perplexity), GumbelSoft shows relatively low perplexity"
>It does not affect writing quality at all, provably
Prove it, then? It's not a claim that GumbelSoft paper makes: "Regarding generation quality (perplexity), GumbelSoft shows relatively low perplexity"