DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models
For developers and users of personalized LLMs, this work identifies and quantifies a previously unmeasured failure mode where memory biases reasoning, which is only partially mitigated by current alignment methods.
The paper introduces DRIFTLENS, a framework to measure how user-attribute memory alters reasoning trajectories in personalized LLMs, finding medium-to-large drift across models and attributes even when answers remain plausible. Post-training methods (GRPO, DPO) reduce drift but with inconsistent effects on other capabilities.
Personalization changes what a model says to a user; we show that it can also change the reasoning trajectory used to justify the response. Modern LLMs personalize interactions by storing user attributes, preferences, and prior context, then injecting this information into future prompts. We study whether such memory reshapes reasoning on open-ended questions where no single ground-truth answer exists. To quantify this effect, we introduce DRIFTLENS, a ground-truth-free framework that maps each expressed reasoning step to a value category and measures divergence between a question's no-memory trajectory and its trajectory under injected user-attribute memory. We first validate that DRIFTLENS distinguishes content-free pragmatic noise from substantive reasoning changes. Across four LLMs and 10 user-attribute categories, including age, occupation, and disability, user-attribute memory induces medium-to-large reasoning drift above each model's pragmatic-noise floor, even when final answers remain fluent, on-topic, and plausible. We then evaluate GRPO- and DPO-based post-training methods for reducing drift. Both reduce drift, but neither uniformly dominates; effects on downstream capability, helpfulness, and instruction following are model-and reward-dependent. These results suggest that memory-induced reasoning drift is a measurable and only partly mitigated failure mode of personalized language models.