10 Slides on Human Feedback

Add to your list(s) Download to your calendar using vCal

• Max Bartolo (Cohere)
• Friday 08 November 2024, 12:00-13:00
• Zoom link: https://cam-ac-uk.zoom.us/j/4751389294?pwd=Z2ZOSDk0eG1wZldVWG1GVVhrTzFIZz09.

If you have a question about this talk, please contact Suchir Salhan.

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.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Computer Education Research
• Computing Education Research
• Department of Computer Science and Technology talks and seminars
• Graduate-Seminars
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• NLIP Seminar Series
• PMRFPS's
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• Zoom link: https://cam-ac-uk.zoom.us/j/4751389294?pwd=Z2ZOSDk0eG1wZldVWG1GVVhrTzFIZz09
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.