Can you also measure how often the LLM response makes people laugh? Sometimes the responses that aren't attempting a joke are the funniest, and I'd be more interested in stats of which LLM succeed in that metric.
Interesting point - thoughts on how to do this? Honestly most models are not-to-kinda funny so I'd be surprised if there were many lol moments. Oral delivery is something I think is v interesting though
measuring humor might be halfway to measuring taste. congrats on this... really original contribution. wonder if you're planning to evolve the benchmark to incorporate a multi-language dimension. would love to see how Mistral and models built outside the US would perform.
4 comments