
GK
Gihoon Kim, Jeyoung Lee, Suhan Woo, Jangwon Oh, Sekwon Oh, Minsu Jeon, Euntai Kim
· 1 min read
ResearcharXiv cs.AI
Cautious Context Steering for Language Model Personalization
arXiv:2608.05813v2 Announce Type: replace
Abstract: User context can personalize a language model without per-user fine-tuning, but its influence is not equally helpful at every token. Context Steering (CoS) uses a fixed steering strength throughout generation and requires two LM forward passes per step. We propose Cautious Context Steering (CCS), a lightweight adapter that learns when and how strongly to steer a frozen LM using user context. We train the adapter through cautious distillation, using oracle targets built from predictions with and without context. It learns to match the steered distribution where context helps predict the user's preferred token and the context-free base distribution elsewhere. The CCS adapter outperforms both training-free context-based methods and trained personalization baselines in preference alignment across benchmarks. We also introduce GSM8K-P to evaluate task accuracy and task-specific format preferences together. CCS achieves high format adherence while maintaining task accuracy, offering a better balance than the baselines. The CCS adapter adds less than 0.4% of the backbone's parameters. At inference, each decoding step uses one context-conditioned LM forward pass and a lightweight adapter evaluation, reducing generation time on PRISM by approximately 35-36% compared with CoS.
Original source
This story was published by arXiv cs.AI and written by Gihoon Kim, Jeyoung Lee, Suhan Woo, Jangwon Oh, Sekwon Oh, Minsu Jeon, Euntai Kim. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


