Record
- Authors
- Hughes, J.; Sheshadri, A.; Khan, A.; Roger, F.
- Year
- 2025
- Title
- Alignment Faking Revisited: Improved Classifiers and Open Source Extensions
- Published in
- Alignment Science Blog, 8 April 2025
- Type
- Web page
- Links
- https://alignment.anthropic.com/2025/alignment-faking-revisited/
https://github.com/safety-research/open-source-alignment-faking
https://huggingface.co/datasets/jplhughes2/classify_alignment_faking_human_labels - Our note
- Alignment Faking Revisited: Improved Classifiers and Open Source Extensions
- Verification
- url-ok: the web address responds (the page itself is not checked).
https://alignment.anthropic.com/2025/alignment-faking-revisited/: HTTP 200, checked 2026-11-14
https://github.com/safety-research/open-source-alignment-faking: HTTP 200, checked 2026-11-14
https://huggingface.co/datasets/jplhughes2/classify_alignment_faking_human_labels: HTTP 200, checked 2026-11-14 - Id
hughes-2025-alignment-faking-revisited-improved-classifiers-open
Cited on
- Alignment faking in large language models read status: not stated
- Alignment Faking Revisited: Improved Classifiers and Open Source Extensions read status: not stated
- How to Replicate and Extend our Alignment Faking Demo read status: not stated
- Towards training-time mitigations for alignment faking in RL read status: not stated
- Why Do Some Language Models Fake Alignment While Others Don't? read status: not stated
As cited
The pages cite this work in 2 forms.
-
Hughes, J., Sheshadri, A., Khan, A., and Roger, F. (2025). Alignment Faking Revisited: Improved Classifiers and Open Source Extensions. Alignment Science Blog, 8 April 2025. https://alignment.anthropic.com/2025/alignment-faking-revisited/
-
Hughes, J., Sheshadri, A., Khan, A., and Roger, F. (2025). Alignment Faking Revisited: Improved Classifiers and Open Source Extensions. Alignment Science Blog, Anthropic, 8 April 2025. https://alignment.anthropic.com/2025/alignment-faking-revisited/. Code: https://github.com/safety-research/open-source-alignment-faking; labeled data: https://huggingface.co/datasets/jplhughes2/classify_alignment_faking_human_labels
BibLaTeX
@online{hughes-2025-alignment-faking-revisited-improved-classifiers-open,
author = {Hughes, J. and Sheshadri, A. and Khan, A. and Roger, F.},
title = {{Alignment Faking Revisited: Improved Classifiers and Open Source Extensions}},
organization = {Alignment Science Blog, 8 April 2025},
date = {2025},
url = {https://alignment.anthropic.com/2025/alignment-faking-revisited/}
}