S
Study
Academic Library
Search
Dashboard
Shelves
Open access
My library
Review
Bertie Vidgen · Study
Home
/
Author
Bertie Vidgen
7 works
· latest 2025
· 2 institutions
cluster: provisional
ORCID 0000-0002-7892-0814
Works
7 shown
Why human–AI relationships need socioaffective alignment
Humanities and Social Sciences Communications
·
2025
·
5 authors
·
Open access
119
citations
The benefits, risks and bounds of personalizing the alignment of large language models to individuals
Nature Machine Intelligence
·
2024
·
4 authors
113
citations
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)
·
2024
·
5 authors
·
other
·
Open access
76
citations
The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
neural information processing systems
·
2024
·
10 authors
·
other
·
Open access
21
citations
Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback
arXiv (Cornell University)
·
2023
·
4 authors
·
preprint
·
Open access
22
citations
Handling and Presenting Harmful Text in NLP Research
Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
·
2022
·
4 authors
·
other
·
Open access
27
citations
What, when and where of petitions submitted to the UK government during a time of chaos
Policy Sciences
·
2020
·
2 authors
·
Open access
14
citations