PsPLUG: explicit style instructions cause 'personalization collapse' in LLMs, lightweight plug-in fixes it
Yutong Song · hf · 2026-09-28
Personalized LLMs are often expected to follow explicit style instructions, but the paper finds such instructions can undermine the user-specific characteristics personalization methods aim to preserve — a failure mode the authors call "personalization collapse."
They propose PsPLUG, a lightweight plug-in that learns a user-specific residual after accounting for the requested style, and allows tuning personalization strength at inference time. Experiments show existing methods degrade under explicit style instructions, whereas PsPLUG better preserves user preferences while providing precise control over the personalization-style balance.
More from Research
- ZooWork-ShopRanker: LLM-judge-aligned open e-commerce rerankers from 0.6B to 8B — Siqiao Xue · 2026-09-28
- Yoav Goldberg: 29 arXiv papers on JEV just two weeks after its limited release is 'not healthy' — yoavgo · 2026-09-28
- Why Data Efficiency Is Humans' Last Edge — Yet Massive Data Feeding Stays Cheapest — himanshustwts · 2026-09-28
- Harness-Zero: PKU, Google and HKUST Distill Agent Harnesses into Model Weights — AxSaucedo · 2026-09-28
- MultiFlow: coupled flow matching predicts single-cell perturbation responses in unseen cellular contexts — burny_tech · 2026-09-28
- Self-Replicating Programs Emerge from Random Noise in Open-Source Browser Remake of BRLabs' Computational Life — zzznah · 2026-09-28