BEGIN:VCALENDAR
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
VERSION:2.0
BEGIN:VEVENT
DESCRIPTION: For the Automatic Short Answer Grading (ASAG) task in NLP\, af
 ter the dissemination of neural networks and attention based transformer mo
 dels\, researchers shifted their focus to extract crucial syntactic and sem
 antic information to be used in the comparison of blueprint answers to that
  of students. In the first part of our discussion\, the shortcomings and po
 tentials of using transformer models for the task of ASAG will be explored\
 , supported by real life research examples collected in a project group.   
 The introductory first part leads to the second part which is dedicated to 
 the use of Large Language Models (LLMs) for the same answer grading and eva
 luation task. Bearing in mind the ongoing debates about the latent and visi
 ble dangers of using LLMs expansively in many fields\, problems that pertai
 n to the task of ASAG in higher education will be discussed. Certain exampl
 es will be used to at least attempt to represent how such problems can be r
 emedied or limited with the later developments in the field. 
DTEND:20240215T153000
DTSTAMP:20250925T100300
DTSTART:20240215T131500
CLASS:PUBLIC
SEQUENCE:0
SUMMARY:BHDL: Potentials of AI in the Analysis and Evaluation of Essay-type
  tasks
UID:152131099@/www.ki.fu-berlin.de
URL:https://www.ki.fu-berlin.de/veranstaltungen/potentials-ai-essay.html
END:VEVENT
END:VCALENDAR