Record
- Authors
- Kadavath, S.; Conerly, T.; Askell, A.; Henighan, T.; Drain, D.; et al.
- Year
- 2022
- Title
- Language Models (Mostly) Know What They Know
- Published in
- arXiv
- Type
- Preprint
- DOI
- 10.48550/arxiv.2207.05221
- arXiv
- arXiv:2207.05221
- Links
- https://arxiv.org/abs/2207.05221
https://www.anthropic.com/research/language-models-mostly-know-what-they-know - Our note
- Language Models (Mostly) Know What They Know
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4285429195 · DOI 10.48550/arxiv.2207.05221 · arXiv:2207.05221 - From the lookup
- doi (the pages' own wording is under "As cited" below)
- Id
kadavath-2022-language-models-mostly-know-what-they
Cited on
- Emergent Introspective Awareness in Large Language Models read status: not stated
- Language Models (Mostly) Know What They Know read status: not stated
- Measuring Progress on Scalable Oversight for Large Language Models read status: not stated
- Studying Large Language Model Generalization with Influence Functions read status: not stated
- Towards Understanding Sycophancy in Language Models read status: not stated
As cited
The pages cite this work in 2 forms.
-
Kadavath, S., Conerly, T., Askell, A., Henighan, T., Drain, D., et al. (2022). Language Models (Mostly) Know What They Know. arXiv:2207.05221.
-
Kadavath, S., Conerly, T., Askell, A., Henighan, T., Drain, D., Perez, E., Schiefer, N., Hatfield-Dodds, Z., DasSarma, N., Tran-Johnson, E., et al. (2022). Language Models (Mostly) Know What They Know. arXiv:2207.05221v4, 21 November 2022. Anthropic. https://arxiv.org/abs/2207.05221. Anthropic page: https://www.anthropic.com/research/language-models-mostly-know-what-they-know
BibLaTeX
@misc{kadavath-2022-language-models-mostly-know-what-they,
author = {Kadavath, S. and Conerly, T. and Askell, A. and Henighan, T. and Drain, D. and others},
title = {{Language Models (Mostly) Know What They Know}},
date = {2022},
doi = {10.48550/arxiv.2207.05221},
eprint = {2207.05221},
eprinttype = {arxiv},
url = {https://www.anthropic.com/research/language-models-mostly-know-what-they-know}
}