Record link: 
http://hdl.handle.net/20.500.12708/224482
-
Title: 
Alignment by Disagreement? Toward Investigating LLMs’ Adaptation to Personal and Sociodemographic Variability in the Perception of Toxicity
en
Citation: 
Pachinger, P., Planitzer, A. M., Neidhardt, J., Hanbury, A., & Lecheler, S. (2025, August 1). Alignment by Disagreement? Toward Investigating LLMs’ Adaptation to Personal and Sociodemographic Variability in the Perception of Toxicity [Conference Presentation]. The 9th Workshop on Online Abuse and Harms (WOAH), Wien, Austria. http://hdl.handle.net/20.500.12708/224482
-
Publication Type: 
Presentation - Conference Presentation
en
Language: 
English
-
Authors: 
Pachinger, Pia 
Planitzer, Anna Maria 
Neidhardt, Julia 
Hanbury, Allan 
Lecheler, Sophie 
-
Organisational Unit: 
E194-04 - Forschungsbereich Data Science 
E056-23 - Fachbereich Innovative Combinations and Applications of AI and ML (iCAIML) 
-
Date (published): 
1-Aug-2025
-
Event name: 
The 9th Workshop on Online Abuse and Harms (WOAH) 
en
Event date: 
31-Jul-2025 - 1-Aug-2025
-
Event place: 
Wien, Austria
-
Keywords: 
Offensiveness detection; Human label variation; dataset creation; text classification; perspectivism; in-context learning
en
Project title: 
Transparente Automatisierte Inhaltsmoderation: ICT20-015 (WWTF Wiener Wissenschafts-, Forschu und Technologiefonds) 
Christian Doppler Labor für Weiterentwicklung des State-of-the-Art von Recommender-Systemen in mehreren Domänen: CDL Neidhardt (Christian Doppler Forschungsgesells) 
-
Research Areas: 
Information Systems Engineering: 100%
-
Science Branch: 
1020 - Informatik: 90%
5020 - Wirtschaftswissenschaften: 10%
-
Appears in Collections:
Presentation

Show full item record

Google ScholarTM

Check