BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//papers.synesthesia.it//ai-heroes-2024//3CBNUU
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-ai-heroes-2024-FS983R@papers.synesthesia.it
DTSTART;TZID=CET:20241211T102000
DTEND;TZID=CET:20241211T110000
DESCRIPTION:In this talk\, we will explore the field of Explainable AI (XAI
 )\, with a particular focus on techniques used to gain insights into Large
  Language Models (LLMs). We will show how XAI can be applied to LLMs\, spe
 cifically analyzing attention maps and the Transformer architecture. Addit
 ionally\, we will walk through the process of building an LLM from scratch
 \, using visualization tools to delve into its inner workings. The talk wi
 ll address key questions surrounding the explainability of LLMs\, such as:
  How can we interpret these vast models? Do LLMs primarily memorize or gen
 eralize? What are the emergent capabilities of LLMs\, and how do they aris
 e?
DTSTAMP:20241209T105218Z
LOCATION:Auditorium
SUMMARY:Explainable AI (XAI) and Large Language Models (LLM): an impossible
  pairing? - Enrico Zimuel\, Leonida Gianfagna
URL:https://papers.synesthesia.it/ai-heroes-2024/talk/FS983R/
END:VEVENT
END:VCALENDAR