让手机输入法学会懂你，实时生成个性化内容。
HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization
- 用用户历史数据微调大模型，实现初始智能预测。
- 分层记忆机制持续学习用户输入习惯，提升个性化效果。
- 专为手机优化，保证低延迟、高隐私的实时输入体验。
移动输入法是文本输入的主要界面，但长期依赖手动打字，难以生成个性化内容。尽管轻量级大语言模型（LLM）使本地辅助生成成为可能，但在设备端实现深度个性化、隐私保护且实时的生成式输入法仍面临根本挑战。为此，我们提出 HUOZIIME，一种由 LLM 驱动的个性化本地输入法。通过在合成个性化数据上对基础模型进行后训练，赋予其类人预测能力；设计分层记忆机制，持续捕捉并利用用户特定输入历史；同时针对设备端部署实施系统级优化，确保在移动约束下高效响应。实验表明，该方法实现了高效的本地执行与高保真度的记忆驱动个性化。代码与包已开源：https://github.com/Shan-HIT/HuoziIME。
原文摘要 · Abstract (English)
Mobile input method editors (IMEs) are the primary interface for text input, yet they remain constrained to manual typing and struggle to produce personalized text. While lightweight large language models (LLMs) make on-device auxiliary generation feasible, enabling deeply personalized, privacy-preserving, and real-time generative IMEs poses fundamental challenges.To this end, we present HUOZIIME, a personalized on-device IME powered by LLM. We endow HUOZIIME with initial human-like prediction ability by post-training a base LLM on synthesized personalization data. Notably, a hierarchical memory mechanism is designed to continually capture and leverage user-specific input history. Furthermore, we perform systemic optimizations tailored to on-device LLMbased IME deployment, ensuring efficient and responsive operation under mobile constraints.Experiments demonstrate efficient on-device execution and high-fidelity memory-driven personalization. Code and package are available at https://github.com/Shan-HIT/HuoziIME.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。