paper-with-me

홈 › Papers

A Framework for Cost-Effective and Self-Adaptive LLM Shaking and Recovery Mechanism

2024-03-12 · Zhiyu Chen, Yu Li, Suochao Zhang, Jingbo Zhou, Jiwen Zhou, Chenfu Bao, dianhai yu

As Large Language Models (LLMs) gain great success in real-world applications, an increasing number of users are seeking to develop and deploy their customized LLMs through cloud services. Nonetheless, in some specific domains, there are still concerns regarding cost and trade-offs between privacy issues and accuracy. In this study, we introduce a cost-effective and self-adaptive LLM shaking tuning and recovery mechanism, named CypherTalk. With carefully designed horizontal and vertical shaking operators, we can achieve comparable accuracy results with SOTA privacy-preserving LLM schemes using Cryptography-based or Differential Privacy-based methods. Experiments also show that with the CypherTalk framework, users can achieve reliable accuracy when using optimized shaking operator settings. To our best knowledge, this is the first work that considers cost, and trade-off between model utility and privacy in LLM scenarios.

📄 PDF Abstract BibTeX arXiv:2403.07283

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preserving

Similar Papers 제목 키워드 기반

Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games

2023-09-27 · Kuo-Hao Ho, Ping-Chun Hsieh, Chiu-Chou Lin, You-Ren Luo 외

In this paper, we propose a new approach called Adaptive Behavioral Costs in Reinforcement Learning (ABC-RL) for training a human-like agent with competitive strength. While deep reinforcement learning agents have recent…

Decision MakingDeep Reinforcement LearningFPS Gamesreinforcement-learning+2

Learning by shaking: Computing policy gradients by physical forward-propagation

2019-09-25 · Arash Mehrjou, Ashkan Soleymani, Stefan Bauer, Bernhard Schölkopf

Model-free and model-based reinforcement learning are two ends of a spectrum. Learning a good policy without a dynamic model can be prohibitively expensive. Learning the dynamic model of a system can reduce the cost of l…

Model-based Reinforcement LearningReinforcement Learning (RL)

Learning to Search for Vehicle Routing with Multiple Time Windows

2025-05-29 · Kuan Xu, Zhiguang Cao, Chenlong Zheng, Linong Liu

In this study, we propose a reinforcement learning-based adaptive variable neighborhood search (RL-AVNS) method designed for effectively solving the Vehicle Routing Problem with Multiple Time Windows (VRPMTW). Unlike tra…

Computational Efficiencyreinforcement-learningReinforcement Learning

Energy Management of Multi-mode Hybrid Electric Vehicles based on Hand-shaking Multi-agent Learning

2022-09-06 · Min Hua, Zhi Li, Quan Zhou

The future transportation system will be a multi-agent network where connected AI agents can work together to address the grand challenges in our age, e.g., mitigation of real-world driving energy consumption. Distinguis…

Deep Reinforcement Learningenergy managementManagementMulti-agent Reinforcement Learning

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning

2024-08-24 · Xinglin Wang, Shaoxiong Feng, Yiwei Li, Peiwen Yuan 외

Self-consistency (SC), a widely used decoding strategy for chain-of-thought reasoning, shows significant gains across various multi-step reasoning tasks but comes with a high cost due to multiple sampling with the preset…