BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:10 Slides on Human Feedback - Max Bartolo (Cohere)
DTSTART:20241108T120000Z
DTEND:20241108T130000Z
UID:TALK222619@talks.cam.ac.uk
CONTACT:Suchir Salhan
DESCRIPTION: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 requirem
 ents\, benefits\, and challenges. We will explore questions along the line
 s of how\, where\, and who human feedback collection does or should concer
 n. Finally\, we will dig deeper into what optimising for human feedback si
 gnals means\, and raise important questions about what we can improve goin
 g forward.\n\n*Speaker Biography*\n\nMax 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 Pon
 tus Stenetorp and Sebastian Riedel\, with the UCL NLP group focused on the
  adversarial robustness of Language Models with humans and models in the l
 oop.
LOCATION:Zoom link: https://cam-ac-uk.zoom.us/j/4751389294?pwd=Z2ZOSDk0eG1
 wZldVWG1GVVhrTzFIZz09
END:VEVENT
END:VCALENDAR