Research
Hypotheses-Guided Self Distillation for Continual Personalization
arXiv:2609.00251v1 Announce Type: new Abstract: As people increasingly interact with LLM assistants in daily life, continually adapting to individual preferences has become essential for effective lon
arXiv:2609.00251v1 Announce Type: new Abstract: As people increasingly interact with LLM assistants in daily life, continually adapting to individual preferences has become essential for effective long-term interactions. However, user preferences are rarely stated in full, and instead emerge through heterogeneous, latent, and noisy signals, with existing methods relying on raw interaction histories or costly reward-based optimization to manage personalization. We introduce HypReflect, a reliable, scalable framework for continual personalization that infers explicit, uncertainty-aware preference hypotheses from diverse user signals, reflectively refines them as new evidence accumulates, and incorporates the resulting user model through hypotheses-guided self-distillation. Experiments across three personalization settings: online personalization, multi-session interactions, and implicit behavioral signals, show that HypReflect outperforms a range of baselines, including raw-history and incremental-update methods. We further demonstrate strong generalization to unseen users and cross-domain settings, along with stability across context budgets, reusable hypotheses, and more focused personalization. These results suggest a step towards reliable and scalable continual personalization through explicit, revisable user preference hypotheses.
Related
- ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition
- SiGMA: Sign-Guided Merging and Adaptation for Multimodal Continual Instruction Tuning
- DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory
Source: arXiv cs.AI | 2026-09-02