CCS is a learned per-token gate for context steering that improves personalized generation on PRISM and four out-of-distribution benchmarks while avoiding a second forward pass per decoding step.
Fast: Feature-aware sampling and tuning for personalized preference alignment with limited data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cautious Context Steering for Language Model Personalization
CCS is a learned per-token gate for context steering that improves personalized generation on PRISM and four out-of-distribution benchmarks while avoiding a second forward pass per decoding step.