paper-with-me

홈 › Papers

CBP-Tuning: Efficient Local Customization for Black-box Large Language Models

2025-09-15 · Jiaxuan Zhao, Naibin Gu, Yuchen Feng, Xiyu Liu, Peng Fu, Zheng Lin, Weiping Wang arxiv

The high costs of customizing large language models (LLMs) fundamentally limit their adaptability to user-specific needs. Consequently, LLMs are increasingly offered as cloud-based services, a paradigm that introduces critical limitations: providers struggle to support personalized customization at scale, while users face privacy risks when exposing sensitive data. To address this dual challenge, we propose Customized Black-box Prompt Tuning (CBP-Tuning), a novel framework that facilitates efficient local customization while preserving bidirectional privacy. Specifically, we design a two-stage framework: (1) a prompt generator trained on the server-side to capture domain-specific and task-agnostic capabilities, and (2) user-side gradient-free optimization that tailors soft prompts for individual tasks. This approach eliminates the need for users to access model weights or upload private data, requiring only a single customized vector per task while achieving effective adaptation. Furthermore, the evaluation of CBP-Tuning in the commonsense reasoning, medical and financial domain settings demonstrates superior performance compared to baselines, showcasing its advantages in task-agnostic processing and privacy preservation.

📄 PDF Abstract BibTeX arXiv:2509.12112

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language Models

2026-03-04 · Liangwei Yang, Shiyu Wang, Haolin Chen, Rithesh Murthy 외 arxiv

As large language models (LLMs) transition from research prototypes to real-world systems, customization has emerged as a central bottleneck. While text prompts can already customize LLM behavior, we argue that text-only…

Privacy-Preserving Prompt Tuning for Large Language Model Services

2023-05-10 · Yansong Li, Zhixing Tan, Yang Liu

Prompt tuning provides an efficient way for users to customize Large Language Models (LLMs) with their private data in the emerging LLM service scenario. However, the sensitive nature of private data brings the need for …

Language ModelingLanguage ModellingLarge Language ModelPrivacy Preserving

Federated Customization of Large Models: Approaches, Experiments, and Insights

2026-01-02 · Yuchuan Ye, Ming Ding, Youjia Chen, Peng Cheng 외 arxiv

In this article, we explore federated customization of large models and highlight the key challenges it poses within the federated learning framework. We review several popular large model customization techniques, inclu…

Knowledge DistillationFederated LearningPrompt Engineering

Subject-driven Video Generation via Disentangled Identity and Motion

2025-04-23 · Daneul Kim, Jingxu Zhang, Wonjoon Jin, Sunghyun Cho 외

We propose to train a subject-driven customized video generation model through decoupling the subject-specific learning from temporal dynamics in zero-shot without additional tuning. A traditional method for video custom…

Subject-driven Video GenerationVideo Generation

Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks

2024-10-03 · Xiaoqun Liu, Jiacheng Liang, Luoxi Tang, Muchao Ye 외

Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerability during this process, where malicious…