BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:STANDARD
DTSTART:20231206T140000
RDATE:20240310T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20241103T010000
RDATE:20250309T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20251102T010000
RDATE:20260308T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20261101T010000
RDATE:20270314T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20271107T010000
RDATE:20280312T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20281105T010000
RDATE:20290311T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240310T030000
RDATE:20241103T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20250309T030000
RDATE:20251102T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RDATE:20261101T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20270314T030000
RDATE:20271107T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20280312T030000
RDATE:20281105T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:1c4f072623033d29abb0263fdf958e00
CATEGORIES:Special Seminar
CREATED:20241202T201542
SUMMARY:Natural Inductive Biases and Generalization in Large Language Models
LOCATION:Hill 705
DESCRIPTION:<p><span data-olk-copy-source="MessageBody" style="font-style: normal; font
 -weight: 400; letter-spacing: normal; text-align: start; text-indent: 0px; 
 text-transform: none; white-space: normal; word-spacing: 0px; text-decorati
 on: none; color: #000000; font-size: 11pt;">Abstract: State-of-the-art larg
 e language models (LLMs) excel in language modeling but require an enormous
  amount of training and struggle to generalize on tasks that are intuitive 
 for humans. In contrast, humans demonstrate a remarkable ability to learn a
 nd generalize from only a few examples.&nbsp; Intriguingly, past work in ps
 ychology and cognitive science has investigated “natural” inductive biases 
 that enable rapid learning and generalization in humans and animals. Despit
 e this, such inductive biases remain largely unexplored in LLMs. To address
  this gap, we recently adopted two classic tasks –transitive inference and 
 associative inference – each of which tests a single well-defined relationa
 l inductive bias that both humans and animals have been found to possess. W
 e will discuss recent work on relational inference in artificial neural net
 works, followed by our ongoing work showing that large language models eith
 er fail to generalize or exhibit brittle generalization on these tasks. Thi
 s is joint work with Kenneth Kay and Samuel Lippl at the Center for Theoret
 ical Neuroscience at Columbia University.</span></p>
CONTACT:Daniel Levine
DTSTAMP:20260827T020848
DTSTART;TZID=America/New_York:20241206T140000
DTEND;TZID=America/New_York:20241206T145000
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR