Why Do Some Language Models Fake Alignment While Others Don't?

Record

Authors
Sheshadri, A.; Hughes, J.; Michael, J.; Mallen, A.; Jose, A.; Janus; Roger, F.
Year
2025
Title
Why Do Some Language Models Fake Alignment While Others Don't?
Published in
arXiv
Type
Preprint
DOI
10.48550/arxiv.2506.18032
arXiv
arXiv:2506.18032
Links
https://arxiv.org/abs/2506.18032
https://openreview.net/forum?id=1Imp4KZyjA
https://openreview.net/pdf?id=1Imp4KZyjA
Our note
Why Do Some Language Models Fake Alignment While Others Don't?
Verification
verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W6947715421 · DOI 10.48550/arxiv.2506.18032 · arXiv:2506.18032
From the lookup
doi, title (the pages' own wording is under "As cited" below)
Id
sheshadri-2025-why-do-some-language-models-fake

Cited on

As cited

The pages cite this work in 4 forms.

  • Sheshadri, A., Hughes, J., Michael, J., et al. (2025). Why Do Some Language Models Fake Alignment While Others Don't? NeurIPS 2025; arXiv:2506.18032.
  • Sheshadri, A., Hughes, J., Michael, J., Mallen, A., Jose, A., Janus, and Roger, F. (2025). Why Do Some Language Models Fake Alignment While Others Don't? In Advances in Neural Information Processing Systems 38 (NeurIPS 2025), spotlight. OpenReview: https://openreview.net/forum?id=1Imp4KZyjA (camera-ready PDF dated 24 October 2025). Preprint: arXiv:2506.18032v1, 22 June 2025, https://arxiv.org/abs/2506.18032.
  • Sheshadri, A., Hughes, J., Michael, J., Mallen, A., Jose, A., Janus, and Roger, F. (2025). Why Do Some Language Models Fake Alignment While Others Don't? In Advances in Neural Information Processing Systems 38 (NeurIPS 2025), spotlight. OpenReview: https://openreview.net/forum?id=1Imp4KZyjA (camera-ready PDF dated 24 October 2025, read from the Internet Archive copy of https://openreview.net/pdf?id=1Imp4KZyjA). Preprint: arXiv:2506.18032v1, 22 June 2025, https://arxiv.org/abs/2506.18032.
  • Sheshadri, A., Hughes, J., Michael, J., Mallen, A., Jose, A., Janus, and Roger, F. (2025). Why Do Some Language Models Fake Alignment While Others Don't? NeurIPS 2025; arXiv:2506.18032.

BibLaTeX

@misc{sheshadri-2025-why-do-some-language-models-fake,
  author = {Sheshadri, A. and Hughes, J. and Michael, J. and Mallen, A. and Jose, A. and {Janus} and Roger, F.},
  title = {{Why Do Some Language Models Fake Alignment While Others Don't?}},
  date = {2025},
  doi = {10.48550/arxiv.2506.18032},
  eprint = {2506.18032},
  eprinttype = {arxiv},
  url = {https://openreview.net/forum?id=1Imp4KZyjA}
}

Download · JSON with CSL-JSON · the whole bibliography