Online Learning with LLM Experts from Limited Feedback
We study adaptive routing of prompts to large language model (LLM) experts to maximize response quality in an online setting with limited feedback. We formulate it as a bandit problem with $K$ actions that represent experts and $d$ features that encode prompts, over a horizon of $T$ rounds. We propose algorithms that s...
Wei Wang, Soumyabrata Pal, Koyel Mukherjee et al.
· 0 citations