What's the Magic Word? A Control Theory of LLM Prompting

Came across this research and thought it is pretty cool: The authors are applying a systematic approach to prompting with the aim of making prompting techniques more explain, more nuances and therefore more accessible.

What is fascinating is that the correct next token following a certain sequence of input tokens is reachable over 97% of the time with prompts of less than 10 input tokens. Intriguingly, short prompt sequences can dramatically alter the likelihood of specific outputs, even making the LEAST likely output tokens become the MOST likely ones.

Here is an interview with the 2 main authors (CalTech): https://www.youtube.com/watch?v=Bpgloy1dDn0

This is the paper: https://arxiv.org/abs/2310.04444

0 comments