Improving LLM Generation with Inverse and Forward Alignment: Reward Modelling, Prompting, Fine‑Tuning, and Inference‑Time Optimisation

H. Sun, T. Pouplin, Nicolás Astorga, T. Liu, Mihaela van der Schaar
Dec 10, 2024
LLMs Alignment
Nicolás Astorga
Nicolás Astorga
Ph.D. student in Machine Learning

Researching reasoning, Bayesian experimental design, and optimisation in/with LLMs.