SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation
This addresses privacy concerns and reasoning limitations in personalized generation for users, though it is incremental as it builds on speculative decoding and collaborative inference.
The paper tackles the dilemma between privacy and reasoning capacity in personalized AI by proposing SpecSteer, an asymmetric collaborative inference framework that synergizes on-device context with cloud reasoning, achieving superior personalized generation performance and a 2.36x speedup over baselines.
Realizing personalized intelligence faces a core dilemma: sending user history to centralized large language models raises privacy concerns, while on-device small language models lack the reasoning capacity required for high-quality generation. Our pilot study shows that purely local enhancements remain insufficient to reliably bridge this gap. We therefore propose SpecSteer, an asymmetric collaborative inference framework that synergizes private on-device context with cloud-scale reasoning. SpecSteer casts collaboration as Bayesian knowledge fusion and repurposes speculative decoding as a distributed alignment protocol, yielding a Draft--Verify--Recover pipeline: the on-device model drafts personalized sequences; the cloud validates via a ratio-based mechanism that decouples reasoning verification from private context, filtering logical flaws without accessing raw user context; upon rejection, a steering recovery injects local intent during correction. Experiments demonstrate that SpecSteer successfully closes the reasoning gap and achieves superior personalized generation performance, while delivering a 2.36x speedup over standard baselines.