BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:America/Los_Angeles
X-WR-TIMEZONE:America/Los_Angeles
BEGIN:VEVENT
UID:248@escience.washington.edu
DTSTART;TZID=America/Los_Angeles:20250116T163000
DTEND;TZID=America/Los_Angeles:20250116T172000
DTSTAMP:20250114T200550Z
URL:https://escience.washington.edu/events/uw-data-science-seminar-xinyi-z
 hou/
SUMMARY:UW Data Science Seminar: Xinyi Zhou
DESCRIPTION:Please join us for a UW Data Science Seminar on Thursday\, Jan
 uary 16th from 4:30 to 5:20 p.m. PT. The seminar will feature Xinyi Zhou\,
  a postdoctoral scholar in the Paul G. Allen School of Computer Science a
 nd Engineering at the University of Washington.\n\nThe seminar will be hel
 d in the Physics/Astronomy Auditorium (PAA)\, Room A118 – campus map.\n
 \n&nbsp\;\n\n"Augmenting LLMs for Social Impact"\n\nAbstract: Large langua
 ge models (LLMs) are undeniably powerful\, but often fall short in terms o
 f trustworthiness and helpfulness in areas like factual accuracy and socia
 l intelligence. This can pose significant challenges when addressing compl
 ex societal issues such as health\, democracy\, science\, and teamwork. In
  this talk\, I will primarily introduce MUSE\, an enhanced LLM that levera
 ges web retrieval and multimodal integration to detect misinformation whil
 e delivering clear\, accurate explanations backed by trustworthy reference
 s. MUSE outperforms top human benchmarks and leading LLMs like GPT-4. Addi
 tionally\, I will present Social-RAG\, a workflow that retrieves from grou
 p interactions to socially ground AI generation\, which powers PaperPing
 —a deployed LLM agent that posts academic paper recommendations in group
  chats without disrupting existing social practices\, fostering group comm
 on ground. I will conclude by discussing broader societal challenges and o
 pportunities in the era of generative AI.\n\nThe 2024-2025 seminars will b
 e held in person\, and are free and open to the public.
ATTACH;FMTTYPE=image/jpeg:https://escience.washington.edu/wp-content/uploa
 ds/2024/12/Xinyi_Zhou_headshot.jpg
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR