Loading...
The system can't perform the operation now. Try again later.
Citations per year
Duplicate citations
The following articles are merged in Scholar. Their
combined citations
are counted only for the first article.
Merged citations
This "Cited by" count includes citations to the following articles in Scholar. The ones marked
*
may be different from the article in the profile.
Add co-authors
Co-authors
Follow
New articles by this author
New citations to this author
New articles related to this author's research
Email address for updates
Done
My profile
My library
Metrics
Alerts
Settings
Sign in
Sign in
Get my own profile
Cited by
All
Since 2019
Citations
25
25
h-index
2
2
i10-index
1
1
0
22
11
2023
2024
3
21
Co-authors
Charlie Rogers-Smith
Verified email at rogerssmith.co.uk
Teun Van Der Weij
MSc Artificial Intelligence student, Utrecht University
Verified email at students.uu.nl
Follow
Simon Lermen
Technical University of Berlin
Verified email at alumni.tu-berlin.de -
Homepage
Articles
Cited by
Co-authors
Title
Sort
Sort by citations
Sort by year
Sort by title
Cited by
Cited by
Year
Lora fine-tuning efficiently undoes safety training in llama 2-chat 70b
S Lermen, C Rogers-Smith, J Ladish
arXiv preprint arXiv:2310.20624
, 2023
18
2023
BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B
P Gade, S Lermen, C Rogers-Smith, J Ladish
arXiv preprint arXiv:2311.00117
, 2023
5
2023
Exploring the Robustness of Model-Graded Evaluations and Automated Interpretability
S Lermen, O Kvapil
arXiv preprint arXiv:2312.03721
, 2023
1
2023
Evaluating Shutdown Avoidance of Language Models in Textual Scenarios
T van der Weij, S Lermen
arXiv preprint arXiv:2307.00787
, 2023
1
2023
The system can't perform the operation now. Try again later.
Articles 1–4
Show more
Privacy
Terms
Help
About Scholar
Search help