Hacker News new | past | comments | ask | show | jobs | submit login

I didn’t even read the paper, I just read the abstract. I was really impressed by the idea of using Shapley values to investigate how each token in a prompt affects the output, including order-based effects.

Even if the paper itself is rubbish I think this approach to studying LLMs at least warrants a second look by another team of researchers.






Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: