The results in an image: https://dl.acm.org/cms/10.1145/3706598.3713470/asset/95dbaf8...
--
From the actual paper ( https://dl.acm.org/doi/10.1145/3706598.3713470 ):
> We used ChatGPT-4o to generate the LLM-generated prompts, while UK-based lawyers generated the lawyer-generated advice
It would have been nice to also have layers assess the LLM output...
I commented on a similar point in a duplicate post: https://news.ycombinator.com/item?id=43819389
Perhaps the mods could combine the dupes.