Dam, H., Knochelmann, J., Joseph, V., & Gopalakrishnan, G. (2025). Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models.
Style de citation Chicago (17e éd.)Dam, Harvey, Jonas Knochelmann, Vinu Joseph, et Ganesh Gopalakrishnan. Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models. 2025.
Style de citation MLA (9e éd.)Dam, Harvey, et al. Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models. 2025.
Attention : ces citations peuvent ne pas être correctes à 100%.