Black-box tuning has attracted recent attention due to that the structure or inner parameters of advanced proprietary models are not accessible. Proxy-tuning provides a test-time output adjustment for tuning black-box language models. It applies the difference of the output logits before and after tuning a smaller white-box "proxy" model to improve the black-box model. However, this technique serves only as a decoding-time algorithm, leading to an inconsistency between training and testing which potentially limits overall performance. To address this problem, we introduce Consistent Proxy Tuning (CPT), a simple yet effective black-box tuning method. Different from Proxy-tuning, CPT additionally exploits the frozen large black-box model and another frozen small white-box model, ensuring consistency between training-stage optimization objective and test-time proxies. This consistency benefits Proxy-tuning and enhances model performance. Note that our method focuses solely on logit-level computation, which makes it model-agnostic and applicable to any task involving logit classification. Extensive experimental results demonstrate the superiority of our CPT in both black-box tuning of Large Language Models (LLMs) and Vision-Language Models (VLMs) across various datasets. The code is available at https://github.com/chunmeifeng/CPT.
Know2Vec: A Black-Box Proxy for Neural Network Retrieval
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；College of Information and Intelligence Engineering, Zhejiang Wanli University（浙江万里学院信息与智能工程学院）；Tsinghua University（清华大学）
Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
Key Lab of High Confidence Software Technologies (Peking University), Ministry of Education（高可信软件技术教育部重点实验室（北京大学））；School of Computer Science, Peking University（北京大学计算机学院）
Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling
Key Lab of Intelligent Information Processing of Chinese Academy of Sciences（中国科学院智能信息处理重点实验室）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Xi’an Jiaotong University（西安交通大学）
RoMA: Robust Model Adaptation for Offline Model-based Optimization
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）；BioMap（百图生科）
Towards Training-free Automatic Proxy Discovery via Large Language Models for Mixed Precision Quantization
School of Computer and Communication Engineering, Northeastern University（东北大学计算机与通信工程学院）；School of Software Engineering, Beijing Jiaotong University（北京交通大学软件工程学院）；School of Software, Northeastern University（东北大学软件学院）
Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
The Pennsylvania State University（宾夕法尼亚州立大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Nanjing University（南京大学）；University of Virginia（弗吉尼亚大学）；NEC Laboratories America（美国NEC实验室）
Beyond the Black Box: An Interpretable Machine Learning Framework for Predicting Electronic Structure Microdescriptors and Structure-Performance Relationships in Fe-based Catalytic Systems
