Record
- Authors
- Greenblatt, R.; Denison, C.; Wright, B.; et al.
- Year
- 2024
- Title
- Alignment faking in large language models
- Published in
- arXiv
- Type
- Preprint
- DOI
- 10.48550/arxiv.2412.14093
- arXiv
- arXiv:2412.14093
- Links
- https://arxiv.org/abs/2412.14093
https://www.anthropic.com/research/alignment-faking - Our note
- Alignment faking in large language models
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4405627013 · DOI 10.48550/arxiv.2412.14093 · arXiv:2412.14093 - From the lookup
- doi (the pages' own wording is under "As cited" below)
- Id
greenblatt-2024-alignment-faking-large-language-models
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
- Auditing language models for hidden objectives read status: not stated
- Claude 3.7 Sonnet System Card read status: secondary
- From shortcuts to sabotage: natural emergent misalignment from reward hacking read status: not stated
- How to Replicate and Extend our Alignment Faking Demo read status: not stated
- System Card: Claude Opus 4 & Claude Sonnet 4 read status: secondary
- 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 5 forms.
-
Greenblatt, R., Denison, C., Wright, B., et al. (2024). Alignment faking in large language models. arXiv:2412.14093.on Alignment Faking Revisited: Improved Classifiers and Open Source Extensions, Auditing language models for hidden objectives, From shortcuts to sabotage: natural emergent misalignment from reward hacking, Towards training-time mitigations for alignment faking in RL, Why Do Some Language Models Fake Alignment While Others Don't?
-
Greenblatt, R., Denison, C., Wright, B., Roger, F., MacDiarmid, M., Marks, S., Treutlein, J., Belonax, T., Chen, J., Duvenaud, D., Khan, A., Michael, J., Mindermann, S., Perez, E., Petrini, L., Uesato, J., Kaplan, J., Shlegeris, B., Bowman, S. R., and Hubinger, E. (2024). Alignment faking in large language models. arXiv:2412.14093v2, 20 December 2024. Anthropic, Redwood Research, New York University, Mila Quebec AI Institute. https://arxiv.org/abs/2412.14093. Anthropic page: https://www.anthropic.com/research/alignment-faking
-
Greenblatt, R., Denison, C., Wright, B., et al. (2024). Alignment faking in large language models. arXiv:2412.14093 (cited by the card for the 15% and 30% figures).
-
Greenblatt, R., Denison, C., Wright, B., et al. (2024). Alignment faking in large language models. arXiv:2412.14093v2, 20 December 2024. https://arxiv.org/abs/2412.14093
-
Greenblatt, R., et al. (2024). Alignment faking in large language models. arXiv:2412.14093 (cited by the card).
BibLaTeX
@misc{greenblatt-2024-alignment-faking-large-language-models,
author = {Greenblatt, R. and Denison, C. and Wright, B. and others},
title = {{Alignment faking in large language models}},
date = {2024},
doi = {10.48550/arxiv.2412.14093},
eprint = {2412.14093},
eprinttype = {arxiv},
url = {https://www.anthropic.com/research/alignment-faking}
}