Record
- Authors
- Cywiński, B.; Ryd, E.; Wang, R.; Rajamanoharan, S.; Nanda, N.; Conmy, A.; Marks, S.
- Year
- 2025
- Title
- Eliciting Secret Knowledge from Language Models
- Published in
- arXiv
- Type
- Preprint
- DOI
- 10.48550/arxiv.2510.01070
- arXiv
- arXiv:2510.01070
- Our note
- none yet
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4414810583 · DOI 10.48550/arxiv.2510.01070 · arXiv:2510.01070 - From the lookup
- doi, title (the pages' own wording is under "As cited" below)
- Id
cywinski-2025-eliciting-secret-knowledge-from-language-models
Cited on
- Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers read status: not stated
- Evaluating honesty and lie detection techniques on a diverse suite of dishonest models read status: not stated
As cited
The pages cite this work in 2 forms.
-
Cywiński, B., Ryd, E., Wang, R., Rajamanoharan, S., Nanda, N., Conmy, A., and Marks, S. (2025). Eliciting secret knowledge from language models. arXiv:2510.01070.
-
Cywiński, B., Ryd, E., Wang, R., Rajamanoharan, S., et al. (2025). Eliciting Secret Knowledge from Language Models. arXiv:2510.01070.
BibLaTeX
@misc{cywinski-2025-eliciting-secret-knowledge-from-language-models,
author = {Cywiński, B. and Ryd, E. and Wang, R. and Rajamanoharan, S. and Nanda, N. and Conmy, A. and Marks, S.},
title = {{Eliciting Secret Knowledge from Language Models}},
date = {2025},
doi = {10.48550/arxiv.2510.01070},
eprint = {2510.01070},
eprinttype = {arxiv}
}