Skip to content
conftrace_
2026 EMNLP EMNLP 2026

DiPer: Disentangled Personal Direction Discovery for Personalized Generation Steering

AbstractLarge Language Model (LLM) personalization aims to adapt generation to individual users by capturing implicit preferences from historical interactions. Steering-based methods offer an inference-efficient solution, but existing work follows a difference-based paradigm that estimates personalized steering directions from representation offsets between contrastive historical examples, thus entangling inherent user preference with preference-agnostic contextual bias. This limitation arises because offset-based estimation uses raw contrastive variation, making the derived direction confounded by contextual bias rather than identifying preference-discriminative variation between user-conditioned and generic behavior. To address this, we propose Disentangled Personal Direction Discovery (DiPer), which formulates personalized steering vector estimation as a discriminative direction discovery problem. DiPer learns layer-wise user-specific directions through supervised metric learning, based on Recursive Feature Machine (CITATION), over historical activations, to discover preference-discriminative directions while suppressing contextual bias. Theoretical analysis and extensive experiments demonstrate DiPer’s efficacy and robustness.

More from EMNLP 2026

All EMNLP 2026 papers →