BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:811@fds.yale.edu
DTSTART;TZID=America/New_York:20241119T160000
DTEND;TZID=America/New_York:20241119T170000
DTSTAMP:20250916T142144Z
URL:https://fds.yale.edu/events/responsible-language-models-knowledge-boun
 dary-awareness/
SUMMARY:FDS Special Seminar: Yi R. (May) Fung (HKUST)\, "Scaling Human-Cent
 ric Trustworthy Foundation Model Reasoning"
DESCRIPTION:\nAbstract: In recent years\, language models have made signifi
 cant advancements\, achieving remarkable performance on a large variety of
  tasks\, as well as promising zero-shot/few-shot capabilities\, bolstered 
 by model scaling and innovative training techniques. Despite the exciting 
 progress\, ensuring these models align with fundamental constitutional pri
 nciples of promoting helpful\, honest\, and harmless information communica
 tion remains a key challenge. In this talk\, we present a roadmap for lang
 uage models to function more responsibly and robustly. First\, we introduc
 e our method for enhancing model reasoning knowledge boundary awareness th
 rough instruction tuning that teaches large language models to say “I do
 n’t know”. Then\, we dive deeper into extending the enhancement of mod
 el knowledge boundary awareness from the language to multimedia domain\, i
 ncluding augmenting the proactive engagement capabilities in model reasoni
 ng. We conclude this talk with a case study of language model self-play se
 lf-learning for greater personalization and scalable oversight\, followed 
 by a discussion of envisioned opportunities and exciting future research d
 irections.\n\n\n\nSpeaker Bio: Yi R. (May) Fung is an Assistant Professor 
 at the HKUST Department of Computer Science and Engineering Department\, a
 nd holds an upcoming affiliate appointment at MIT. She completed her Ph.D.
  at the University of Illinois with Prof. Heng Ji. May’s research focus 
 centers around socially-situated human-centered trustworthy NLP/AI with mu
 ltimedia knowledge reasoning capability and scalable alignment principles.
  She is a recipient of three top AI/NLP conference paper awards\, and is a
 lso organizing the AI4Research Workshop at AAAI’25 this year.\n\n\n\nHos
 ted by Arman Cohan and Robert (Xiangru) Tang\n\n\n\n\n
CATEGORIES:FDS Events,Special Seminar
LOCATION:Yale Institute for Foundations of Data Science\, Kline Tower 13th 
 Floor\, Room 1327\, New Haven\, CT\, 06511\, United States
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Kline Tower 13th Floor\, Ro
 om 1327\, New Haven\, CT\, 06511\, United States;X-APPLE-RADIUS=100;X-TITL
 E=Yale Institute for Foundations of Data Science:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR