FishBack derives a closed-form minimum-distortion steering direction from the pullback Fisher metric of the softmax layer, outperforming Euclidean baselines on GPT-2 verb-morphology tasks with lower off-target KL divergence.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
NLP comparison of lobby papers and MEP speeches discovers influence links validated indirectly via retweets and meetings, achieving AUC 0.77 and ideological alignment in aggregate analysis.
DECOR learns decomposed contextual token representations by combining pretrained semantics with collaborative signals to fix objective misalignment in two-stage generative recommendation systems.
citing papers explorer
-
FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers
FishBack derives a closed-form minimum-distortion steering direction from the pullback Fisher metric of the softmax layer, outperforming Euclidean baselines on GPT-2 verb-morphology tasks with lower off-target KL divergence.
-
Studying Lobby Influence in the European Parliament
NLP comparison of lobby papers and MEP speeches discovers influence links validated indirectly via retweets and meetings, achieving AUC 0.77 and ideological alignment in aggregate analysis.
-
Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation
DECOR learns decomposed contextual token representations by combining pretrained semantics with collaborative signals to fix objective misalignment in two-stage generative recommendation systems.