BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Mapping the (Jagged) Landscape of LLM Capabilities - Prof. Peter W
 est (University of British Columbia)
DTSTART:20251127T160000Z
DTEND:20251127T170000Z
UID:TALK237781@talks.cam.ac.uk
CONTACT:Lucas Resck
DESCRIPTION:Abstract:\n\nOne key missing piece for the broad adoption of L
 LMs is intuition\, specifically\, human intuition about when and how model
 s will succeed or fail across the diverse tasks we might apply them to. Yo
 ur LLM might write a well-reasoned essay on 14th-century theology\, but do
 es that mean it can accurately answer questions on the same topic? This ta
 lk will focus on one aspect of my research\, which is the characterization
  of model capabilities to begin to develop these intuitions. I will discus
 s recent projects that try to identify where these capabilities break down
 \, with a particular focus on high information examples which will necessi
 tate new hypotheses of how exactly artificial intelligence functions. \n\n
 Bio:\n\nPeter West is an assistant professor at the University of British 
 Columbia\, broadly working on the capabilities and limits of LLMs. For exa
 mple: the divergence of AI from human intuitions of intelligence\, unpredi
 ctability and creativity in models\, and studying LLMs with a non-interven
 tional natural sciences lens. Peter completed his PhD at the University of
  Washington\, Paul G School of Computer Science and Engineering. He comple
 ted a postdoc at the Stanford Institute for Human-Centered AI. His work ha
 s been recognized with best\, outstanding\, and spotlight papers in NLP an
 d AI conferences. 
LOCATION:https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBd
 XVpOXFvdz09
END:VEVENT
END:VCALENDAR