面向动态端侧 LLM 个性化的自适应自监督学习策略
Adaptive Self-Supervised Learning Strategies for Dynamic On-Device LLM Personalization
AI总结：
针对端侧 LLM 个性化挑战，提出自适应自监督学习策略 ASLS，通过用户画像层与神经适应层实现实时微调与持续学习，有效降低计算需求并提升个性化效率及用户满意度。
摘要：
大型语言模型（LLMs）彻底改变了我们与技术交互的方式，但将其个性化以适应个人用户偏好仍是一项重大挑战，尤其是在端侧应用中。传统方法通常严重依赖标注数据集，且可能资源消耗较大。为解决这些问题，我们提出了自适应自监督学习策略（ASLS），利用自监督学习技术动态实现 LLMs 的个性化。该框架包含用于收集交互数据的用户画像层，以及用于实时模型微调的神经适应层。这一创新方法支持从用户反馈中持续学习，使模型能够生成紧密契合用户特定上下文的响应。ASLS 的自适应机制降低了计算需求并提升了个性化效率。在各种用户场景下的实验结果表明，ASLS 在提升用户参与度和满意度方面表现出卓越性能，凸显了其将 LLMs 重新定义为端侧高响应性和上下文感知系统的潜力。
英文摘要：
Large language models (LLMs) have revolutionized how we interact with technology, but their personalization to individual user preferences remains a significant challenge, particularly in on-device applications. Traditional methods often depend heavily on labeled datasets and can be resource-intensive. To address these issues, we present Adaptive Self-Supervised Learning Strategies (ASLS), which utilizes self-supervised learning techniques to personalize LLMs dynamically. The framework comprises a user profiling layer for collecting interaction data and a neural adaptation layer for real-time model fine-tuning. This innovative approach enables continuous learning from user feedback, allowing the model to generate responses that align closely with user-specific contexts. The adaptive mechanisms of ASLS minimize computational demands and enhance personalization efficiency. Experimental results across various user scenarios illustrate the superior performance of ASLS in boosting user engagement and satisfaction, highlighting its potential to redefine LLMs as highly responsive and context-aware systems on-device.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
