Faithful Persona Steering under Incongruity via Dual-Stream Refinement

摘要

Standard LLM personalization typically frames identity as a static retrieval task, overlooking the inherent incongruity of human personas, where stable traits coexist with atypical, context-specific stances. Existing methods struggle to reconcile these dimensions: prompting succumbs to context drift over long sequences, while fine-tuning often suppresses idiosyncratic “quirks” in favor of generic distributional patterns. To bridge this gap, we present QuirkyMind, a framework that disentangles identity definition from its expression. First, Traits Anchoring constructs a dual-stream latent state, fusing a sentence-level summary for semantic stability with a token-level sequence for generative control. This state is stabilized via In-Context Narrative Refinement using an alternating objective: a discriminative InfoNCE loss anchors the persona in representation space to prevent drift, while a generative cross-entropy loss ensures faithful verbalization. Finally, Persona Steered Generalization transfers the refined state to downstream tasks via parameter-efficient adapters. Empirical evaluations on Persona-Steered QA and Narrative Inference demonstrate that QuirkyMind mitigates drift, consolidating persona knowledge without erasing authentic incongruities.