unibiblio > ubs_30221

bookmarks (hide)
display
all
bookmarks only
bookmarks per page
5
10
20
50
100
sort by
added at
title
RSS
BibTeX
XML

No matching posts.

⟨⟨
⟨
⟩
⟩⟩

publications (hide)41
display
all
publications only
publications per page
5
10
20
50
100
sort by
added at
title
author
publication date
entry type
help for advanced sorting...
BibTeX
CSV
RDF
RSS
more...

2Large Reasoning Models Are Autonomous Jailbreak Agents
T. Hagendorff, E. Derner, and N. Oliver. Nature Communications, (2025)
22 days ago by @unibiblio
show all tags
oa
sent
ubs_10021
ubs_20018
ubs_30221
ubs_40452
unibibliografie
oasentubs_10021ubs_20018ubs_30221ubs_40452unibibliografie
copydeleteadd this publication to your clipboard
1“I understand your perspective” : LLM Persuasion through the Lens of Communicative Action Theory
E. Dönmez, and A. Falenska. Findings of the Association for Computational Linguistics: ACL 2025, page 15312-15327. Association for Computational Linguistics, (2025)
22 days ago by @unibiblio
show all tags
mult
sent
ubs_10005
ubs_10021
ubs_20008
ubs_20018
ubs_30081
ubs_30221
ubs_40111
unibibliografie
multsentubs_10005ubs_10021ubs_20008ubs_20018ubs_30081ubs_30221ubs_40111unibibliografie
copydeleteadd this publication to your clipboard
2PRIDE : Parameter-Efficient Reduction of Identity Discrimination for Equality in LLMs
M. Menke, and T. Hagendorff. Preprint, (2025)
22 days ago by @unibiblio
show all tags
sent
ubs_10021
ubs_20018
ubs_30221
ubs_40452
unibibliografie
sentubs_10021ubs_20018ubs_30221ubs_40452unibibliografie
copydeleteadd this publication to your clipboard
2On the Inevitability of Left-Leaning Political Bias in Aligned Language Models
T. Hagendorff. Preprint, (2025)
22 days ago by @unibiblio
show all tags
sent
ubs_10021
ubs_20018
ubs_30221
ubs_40452
unibibliografie
sentubs_10021ubs_20018ubs_30221ubs_40452unibibliografie
copydeleteadd this publication to your clipboard
2Uncovering latent profiles of political news consumers and their associations with political views and their extremity
C. Sindermann. Discover psychology, 4 (1): 207 (2024)
a month ago by @unibiblio
show all tags
oa
sent
ubs_10021
ubs_20018
ubs_30221
unibibliografie
oasentubs_10021ubs_20018ubs_30221unibibliografie
copydeleteadd this publication to your clipboard
2Toxic disinhibition makes a versatile rulebreaker in cyberspace : Mapping online deviance with exploratory graph analysis and structural equation modeling
H. Schmitt, C. Sindermann, and C. Montag. Acta psychologica, 260 (October): 105542 (2025)
2 months ago by @unibiblio
show all tags
oa
ubs_10021
ubs_20018
ubs_30221
unibibliografie
wos
oaubs_10021ubs_20018ubs_30221unibibliografiewos
copydeleteadd this publication to your clipboard
2Investigating toxicity and bias in stable diffusion text-to-image models
M. Schneider, and T. Hagendorff. Scientific reports, (2025)
3 months ago by @unibiblio
show all tags
oa
sent
ubs_10021
ubs_20018
ubs_30221
ubs_40452
unibibliografie
oasentubs_10021ubs_20018ubs_30221ubs_40452unibibliografie
copydeleteadd this publication to your clipboard
2Performance expectancy benefits acceptance towards digital support for self-regulation
M. Wirzberger, L. Bareiß, V. Herbst, A. Stock, and J. Kembitzky. Acta psychologica, 258 (August): 105273 (2025)
4 months ago by @unibiblio
show all tags
f2025
gold
mult
oa
oafonds
transform
ubs_10011
ubs_10021
ubs_20016
ubs_20018
ubs_30149
ubs_30221
ubs_40413
ubs_40536
unibibliografie
wos
f2025goldmultoaoafondstransformubs_10011ubs_10021ubs_20016ubs_20018ubs_30149ubs_30221ubs_40413ubs_40536unibibliografiewos
copydeleteadd this publication to your clipboard
1Is (problematic) social media use stressing me out and making me depressed? Insights from a study implementing mobile sensing and self-report methodology
N. Löchner, D. Rozgonjuk, C. Sindermann, and C. Montag. volume 13 of Journal of behavioral addictions, page 228. Akadémiai Kiadó, (2024)
4 months ago by @unibiblio
show all tags
oa
ubs_10021
ubs_20018
ubs_30221
unibibliografie
wos
oaubs_10021ubs_20018ubs_30221unibibliografiewos
copydeleteadd this publication to your clipboard
1Willingness to pay for the messenger WhatsApp, taking into account personality and sent/received messages
C. Kannen, C. Sindermann, and C. Montag. 13, Supplement1, page 315. Akadémiai Kiadó, (2024)
4 months ago by @unibiblio
show all tags
oa
ubs_10021
ubs_20018
ubs_30221
unibibliografie
wos
oaubs_10021ubs_20018ubs_30221unibibliografiewos
copydeleteadd this publication to your clipboard
2Toward an Integrated Psychological Model of Violent Extremism
M. Obaidi, R. Bergh, S. Ozer, and C. Sindermann. European review of social psychology, (2025)
5 months ago by @unibiblio
show all tags
oa
ubs_10021
ubs_20018
ubs_30221
unibibliografie
wos
oaubs_10021ubs_20018ubs_30221unibibliografiewos
copydeleteadd this publication to your clipboard
1Analyzing the Interest in Digital Wellbeing Services : Are People More Willing to Pay for Them on Social Network Sites or Messaging Platforms?
S. Alshakhsi, A. Babiker, D. Al-Thani, C. Sindermann, C. Montag, and R. Ali. (2024)
6 months ago by @unibiblio
show all tags
dimensions
ubs_10021
ubs_20018
ubs_30221
unibibliografie
dimensionsubs_10021ubs_20018ubs_30221unibibliografie
copydeleteadd this publication to your clipboard
5Mapping the Ethics of Generative AI : a Comprehensive Scoping Review
T. Hagendorff. Minds and machines, (2024)
7 months ago by @unibiblio
show all tags
f2024
hybrid
oa
oafonds
transform
ubs_10021
ubs_20018
ubs_30221
ubs_40452
unibibliografie
f2024hybridoaoafondstransformubs_10021ubs_20018ubs_30221ubs_40452unibibliografie
copydeleteadd this publication to your clipboard
3When Image Generation Goes Wrong : A Safety Analysis of Stable Diffusion Models
M. Schneider, and T. Hagendorff. Preprint, (2024)
9 months ago by @unibiblio
show all tags
sent
ubs_10021
ubs_20018
ubs_30221
ubs_40452
unibibliografie
sentubs_10021ubs_20018ubs_30221ubs_40452unibibliografie
copydeleteadd this publication to your clipboard
3A Looming Replication Crisis in Evaluating Behavior in Language Models? : Evidence and Solutions
L. Vaugrante, M. Niepert, and T. Hagendorff. Preprint, (2024)
9 months ago by @unibiblio
show all tags
mult
sent
ubs_10005
ubs_10021
ubs_20008
ubs_20018
ubs_30221
ubs_30223
ubs_40452
ubs_40486
unibibliografie
multsentubs_10005ubs_10021ubs_20008ubs_20018ubs_30221ubs_30223ubs_40452ubs_40486unibibliografie
copydeleteadd this publication to your clipboard
3Fairness Hacking : The Malicious Practice of Shrouding Unfairness in Algorithms
K. Meding, and T. Hagendorff. Philosophy & technology, 37 (4): 1-22 (2024)
10 months ago by @unibiblio
show all tags
f2024
hybrid
oafonds
transform
ubs_10021
ubs_20018
ubs_30221
ubs_40452
unibibliografie
f2024hybridoafondstransformubs_10021ubs_20018ubs_30221ubs_40452unibibliografie
copydeleteadd this publication to your clipboard
2Investigating autistic traits, social phobia, fear of COVID-19, and internet use disorder variables in the context of videoconference fatigue
Y. Zhang, S. Yao, C. Sindermann, D. Rozgonjuk, M. Zhou, R. Riedl, and C. Montag. Telematics and informatics reports, 11 (September): 100067 (2023)
10 months ago by @unibiblio
show all tags
abgleich
oa
ubs_10021
ubs_20018
ubs_30221
unibibliografie
abgleichoaubs_10021ubs_20018ubs_30221unibibliografie
copydeleteadd this publication to your clipboard
1Please note that I’m just an AI : Analysis of Behavior Patterns of LLMs in (Non-)offensive Speech Identification
E. Dönmez, N. Vu, and A. Falenska. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, page 18340-18357. Association For Computational Linguistics, (2024)
10 months ago by @unibiblio
show all tags
mult
sent
ubs_10005
ubs_10021
ubs_20008
ubs_20018
ubs_30081
ubs_30221
ubs_40111
ubs_40407
unibibliografie
multsentubs_10005ubs_10021ubs_20008ubs_20018ubs_30081ubs_30221ubs_40111ubs_40407unibibliografie
copydeleteadd this publication to your clipboard
2To Follow or Not to Follow : Estimating Political Opinion From Twitter Data Using a Network-Based Machine Learning Approach
N. Brandenstein, C. Montag, and C. Sindermann. Social science computer review, (2024)
10 months ago by @unibiblio
show all tags
oa
sent
ubs_10021
ubs_20018
ubs_30221
unibibliografie
oasentubs_10021ubs_20018ubs_30221unibibliografie
copydeleteadd this publication to your clipboard
1HNC : Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities
E. Dönmez, P. Tilli, H. Yang, N. Vu, and C. Silberer. Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), page 364-388. Association For Computational Linguistics, (2023)
10 months ago by @unibiblio
show all tags
mult
sent
ubs_10005
ubs_10021
ubs_20008
ubs_20018
ubs_30081
ubs_30221
ubs_40108
ubs_40407
unibibliografie
multsentubs_10005ubs_10021ubs_20008ubs_20018ubs_30081ubs_30221ubs_40108ubs_40407unibibliografie
copydeleteadd this publication to your clipboard

⟨⟨
⟨
1
2
3
⟩
⟩⟩

PUMA

bookmarks (hide)
display
all
bookmarks only
bookmarks per page
5
10
20
50
100
sort by
added at
title
RSS
BibTeX
XML

publications (hide)41
display
all
publications only
publications per page
5
10
20
50
100
sort by
added at
title
author
publication date
entry type
help for advanced sorting...
BibTeX
CSV
RDF
RSS
more...

2Large Reasoning Models Are Autonomous Jailbreak Agents

1“I understand your perspective” : LLM Persuasion through the Lens of Communicative Action Theory

2PRIDE : Parameter-Efficient Reduction of Identity Discrimination for Equality in LLMs

2On the Inevitability of Left-Leaning Political Bias in Aligned Language Models

2Uncovering latent profiles of political news consumers and their associations with political views and their extremity

2Toxic disinhibition makes a versatile rulebreaker in cyberspace : Mapping online deviance with exploratory graph analysis and structural equation modeling

2Investigating toxicity and bias in stable diffusion text-to-image models

2Performance expectancy benefits acceptance towards digital support for self-regulation

1Is (problematic) social media use stressing me out and making me depressed? Insights from a study implementing mobile sensing and self-report methodology

1Willingness to pay for the messenger WhatsApp, taking into account personality and sent/received messages

2Toward an Integrated Psychological Model of Violent Extremism

1Analyzing the Interest in Digital Wellbeing Services : Are People More Willing to Pay for Them on Social Network Sites or Messaging Platforms?

5Mapping the Ethics of Generative AI : a Comprehensive Scoping Review

3When Image Generation Goes Wrong : A Safety Analysis of Stable Diffusion Models

3A Looming Replication Crisis in Evaluating Behavior in Language Models? : Evidence and Solutions

3Fairness Hacking : The Malicious Practice of Shrouding Unfairness in Algorithms

2Investigating autistic traits, social phobia, fear of COVID-19, and internet use disorder variables in the context of videoconference fatigue

1Please note that I’m just an AI : Analysis of Behavior Patterns of LLMs in (Non-)offensive Speech Identification

2To Follow or Not to Follow : Estimating Political Opinion From Twitter Data Using a Network-Based Machine Learning Approach

1HNC : Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities

browse

related tags

concepts

tags

bookmarks (hide) displayallbookmarks onlybookmarks per page5102050100 sort byadded attitle RSSBibTeXXML

publications (hide)41 displayallpublications onlypublications per page5102050100 sort byadded attitleauthorpublication dateentry typehelp for advanced sorting... BibTeXCSVRDFRSSmore...

browse

related tags

tags

bookmarks (hide)
display
all
bookmarks only
bookmarks per page
5
10
20
50
100
sort by
added at
title
RSS
BibTeX
XML

publications (hide)41
display
all
publications only
publications per page
5
10
20
50
100
sort by
added at
title
author
publication date
entry type
help for advanced sorting...
BibTeX
CSV
RDF
RSS
more...