Efficient and accurate steering of large language models through attention-guided feature learning.

Davarmanesh P, Wilson A, Radhakrishnan A

Open source

DOI
10.1073/pnas.2609978123
Published
2026 Oct 20
Container
Proceedings of the National Academy of Sciences of the United States of America
Publisher
Not recorded
Open access
yes

Credibility signals

limited evidence Score 45/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.1073/pnas.2609978123,
  title = {Efficient and accurate steering of large language models through attention-guided feature learning.},
  author = {Davarmanesh P and Wilson A and Radhakrishnan A},
  year = {2026},
  journal = {Proceedings of the National Academy of Sciences of the United States of America},
  doi = {10.1073/pnas.2609978123},
  url = {https://doi.org/10.1073/pnas.2609978123}
}

RIS

TY  - JOUR
TI  - Efficient and accurate steering of large language models through attention-guided feature learning.
AU  - Davarmanesh P
AU  - Wilson A
AU  - Radhakrishnan A
PY  - 2026
JO  - Proceedings of the National Academy of Sciences of the United States of America
DO  - 10.1073/pnas.2609978123
UR  - https://doi.org/10.1073/pnas.2609978123
ER  - 

APA

P, D., A, W., & A, R. (2026). Efficient and accurate steering of large language models through attention-guided feature learning.. Proceedings of the National Academy of Sciences of the United States of America. https://doi.org/10.1073/pnas.2609978123

Source records