Hard-thresholding next tokens by a safety value function yields higher expected safety, an explicit type-I intervention bound controlled by one threshold, and better empirical safety-helpfulness-similarity trade-offs than Gibbs-style or ARGS steering.
Gedi: Generative discriminator guided sequence generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2roles
background 1polarities
background 1representative citing papers
Neuron Auctions auction continuous neuron intervention budgets on brand-specific orthogonal subspaces in LLMs to achieve strategy-proof revenue optimization while penalizing user utility loss.
citing papers explorer
-
Selective Safety Steering via Value-Filtered Decoding
Hard-thresholding next tokens by a safety value function yields higher expected safety, an explicit type-I intervention bound controlled by one threshold, and better empirical safety-helpfulness-similarity trade-offs than Gibbs-style or ARGS steering.
-
LLM Advertisement based on Neuron Auctions
Neuron Auctions auction continuous neuron intervention budgets on brand-specific orthogonal subspaces in LLMs to achieve strategy-proof revenue optimization while penalizing user utility loss.