Positional preferences, order effects, prompt sensitivity undermine AI judgments
Link: https://www.cip.org/blog/llm-judges-are-unreliable
Discussion: https://news.ycombinator.com/item?id=44074668
Positional preferences, order effects, prompt sensitivity undermine AI judgments
Link: https://www.cip.org/blog/llm-judges-are-unreliable
Discussion: https://news.ycombinator.com/item?id=44074668
If you have a fediverse account, you can quote this note from your own instance. Search https://social.lansky.name/users/hn100/statuses/114560120191130389 on your instance and quote it. (Note that quoting is not supported in Mastodon.)