BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards Knowledgeable Foundation Models - Heng Ji\, UIUC
DTSTART:20241121T153000Z
DTEND:20241121T163000Z
UID:TALK222280@talks.cam.ac.uk
CONTACT:Tiancheng Hu
DESCRIPTION:Abstract: Large language models (LLMs) and vision-language mod
 els (VLMs) have demonstrated remarkable performance on knowledge reasoning
  tasks\, owing to their implicit knowledge derived from extensive pretrain
 ing data. However\, their inherent knowledge bases often suffer from disor
 ganization and illusion\, bias towards common entities\, and rapid obsoles
 cence. Consequently\, LLMs frequently make up untruthful information\, exh
 ibit resistance to updating outdated knowledge\, or struggle with generali
 zing across multiple languages. In this talk I will discuss several resear
 ch directions that aim to make foundation models’ knowledge more accurat
 e\, organized\, up-to-date and fair: (1) Where and How is Knowledge Stored
  in LLM? (2) How to Control LLM’s Knowledge? (3) How to Update LLM’s D
 ynamic Knowledge? (4) How to Bridge the Knowledge Gap between Natural Lang
 uage and Unnatural Language?\n \nBio:\nHeng Ji is a professor at Siebel Sc
 hool of Computing and Data Science\, and an affiliated faculty member at E
 lectrical and Computer Engineering Department\, Coordinated Science Labora
 tory\, and Carl R. Woese Institute for Genomic Biology of University of Il
 linois Urbana-Champaign. She is an Amazon Scholar. She is the Founding Dir
 ector of Amazon-Illinois Center on AI for Interactive Conversational Exper
 iences (AICE). She received her B.A. and M. A. in Computational Linguistic
 s from Tsinghua University\, and her M.S. and Ph.D. in Computer Science fr
 om New York University. Her research interests focus on Natural Language P
 rocessing\, especially on Multimedia Multilingual Information Extraction\,
  Knowledge-enhanced Large Language Models and Vision-Language Models\, and
  AI for Science. The awards she received include Outstanding Paper Award a
 t ACL2024\, two Outstanding Paper Awards at NAACL2024\, "Young Scientist" 
 by the World Laureates Association in 2023 and 2024\, "Young Scientist" an
 d a member of the Global Future Council on the Future of Computing by the 
 World Economic Forum in 2016 and 2017\, "Women Leaders of Conversational A
 I" (Class of 2023) by Project Voice\, "AI's 10 to Watch" Award by IEEE Int
 elligent Systems in 2013\, NSF CAREER award in 2009\, PACLIC2012 Best pape
 r runner-up\, "Best of ICDM2013" paper award\, "Best of SDM2013" paper awa
 rd\, ACL2018 Best Demo paper nomination\, ACL2020 Best Demo Paper Award\, 
 NAACL2021 Best Demo Paper Award\, Google Research Award in 2009 and 2014\,
  IBM Watson Faculty Award in 2012 and 2014 and Bosch Research Award in 201
 4-2018. She served as the associate editor for IEEE/ACM Transaction on Aud
 io\, Speech\, and Language Processing\, and the Program Committee Co-Chair
  of many conferences including NAACL-HLT2018 and AACL-IJCNLP2022. She was 
 elected as the North American Chapter of the Association for Computational
  Linguistics (NAACL) secretary 2020-2023.\n 
LOCATION:https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBd
 XVpOXFvdz09
END:VEVENT
END:VCALENDAR