In this talk, Max Bartolo will share a brief overview of the critical role human feedback plays in enhancing Large Language Model (LLM) performance and aligning model behaviours to human expectations. We will delve into key aspects of human feedback, examining some of its requirements, benefits, and challenges. We will explore questions along the lines of how, where, and who human feedback collection does or should concern. Finally, we will dig deeper into what optimising for human feedback signals means, and raise important questions about what we can improve going forward.
*Speaker Biography*
Max Bartolo is a researcher at Cohere leading the post-training team (Command), and working group co-chair for Dynabench at MLCommons. He completed a PhD, under the supervision of Pontus Stenetorp and Sebastian Riedel, with the UCL NLP group focused on the adversarial robustness of Language Models with humans and models in the loop.
