研究库 论文知识库

内容库 / 论文

arXiv:2601.06362 · LLM 基础设施

Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs

Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs

类型：arxiv
标识：2601.06362
链接：https://arxiv.org/abs/2601.06362
主分类：llm-infra
形态：method
TLDR：Personalized large language models are often expected to follow explicit style instructions, yet we find that such instructions can undermine the user-specific characteristics that personalization methods aim to preserve. We call this failure mode personalization collapse: explicit style control can conflict with implicit user preferences. To address this challenge, we propose PsPLUG, a lightweight plug-in that learns a user-specific residual after accounting for the requested style. PsPLUG also allows us to tune personalization strength at inference time. Our experiments show that explicit st
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-28-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记精读与批判 v2 · Image Tokenizers as Visual Languages in Unified Multimodal Models · 2026-09-12 中午棒（重写覆盖）

笔记精读：Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects

笔记 2026-07-04 上午多模态对照精读 · Seeker（文本→像素的长上下文 MLLM）

仓库 leon2k2k2k/llm-feedback-alignment

仓库 Erikalaylafajri15/MOSS-VL

文档 Tom-on-flyP-2026-07-16

arXiv

2601.06362

TLDR

Personalized large language models are often expected to follow explicit style instructions, yet we find that such instructions can undermine the user-specific characteristics that personalization methods aim to preserve. We call this failure mode personalization collapse: explicit style control can conflict with implicit user preferences. To address this challenge, we propose PsPLUG, a lightweight plug-in that learns a user-specific residual after accounting for the requested style. PsPLUG also allows us to tune personalization strength at inference time. Our experiments show that explicit st

相关解读

arXiv ↗ 中文全文