BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Modeling Human Cognitive Processes for Reasoning in LLMs
DTSTART:20250826T170000
DTEND:20250826T190000
DTSTAMP:20261108T192514Z
UID:a38fe0db50fc836e61098811da5d6363ced6d3609f31475b2b313cb1
CATEGORIES:Conferences - Seminars
DESCRIPTION:Marta Knezevic\nEDIC candidacy exam\nExam president: Prof. Ant
 oine Bosselut\nThesis advisor: Prof. Tanja Käser\nCo-examiner: Prof. Mart
 in Schrimpf\n\nAbstract\nThis thesis explores learning by interaction and 
 in-context learning in humans and LLMs. We investigate how large LLMs can 
 be guided toward more human-like reasoning by aligning their learning and 
 inference processes with cognitive science and educational theory. Drawing
  from principles such as metacognition\, analogical reasoning\, and strate
 gic behavior\, the research investigates how human-inspired concepts can i
 mprove LLMs' ability to do inductive reasoning\, hypothesize\, learn from 
 mistakes and reflect on their own outputs. This work aims to bridge the ga
 p between human and machine learning and uncover shared principles of repr
 esentation\, abstraction\, and reasoning that drive intelligent behavior i
 n both\n\nSelected papers\ncoming soon
LOCATION:INF 220 https://plan.epfl.ch/?room==INF%20220
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR