BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine Theory of Mind and it's Applications - Adil Soubki (Univer
 sity of Cambridge)
DTSTART:20251118T140000Z
DTEND:20251118T150000Z
UID:TALK241033@talks.cam.ac.uk
CONTACT:Sven Krippendorf
DESCRIPTION:In the late 1970s\, the term theory of mind (ToM) was coined b
 y psychologists studying the behavior of chimpanzees to describe the abili
 ty of individuals to attribute mental states to themselves and others. Soo
 n after\, inquiry also turned towards humans. In recent years there has be
 en an enormous interest in studying ToM in machines (i.e.\, machine theory
  of mind) -- especially in language models (LMs). Such inferences underlie
  many of LMs most studied behaviors: intention recognition\, belief predic
 tion\, deception\, emotion labeling\, reading comprehension\, and many mor
 e all rely on models that can generalize this reasoning to disparate conte
 xts. I'll talk about some approaches to machine ToM across three levels: m
 odeling individual mental states (such as belief\, hedging\, and common gr
 ound)\; reasoning over socially shared or group beliefs (including politen
 ess and face-management)\; and some attempts to find methods that generali
 ze across ToM tasks.
LOCATION:DAMTP\, MR11
END:VEVENT
END:VCALENDAR