用可解释性选预个性化模型，让手机端大模型更快更省数据地定制。
Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection
- 基于可解释性挑选已个性化模型，避免从零训练。
- 计算成本降低83%，数据效率提升51%。
- 适合注重隐私和算力受限的移动端个性化场景。
大型语言模型（LLMs）的个性化在实际应用中至关重要，以满足不同移动用户的需求。由于数据隐私问题，个性化通常需在用户手机本地完成，但受限于设备算力和用户个人数据不足。本文提出XPerT技术，通过微调已有个性化模型并基于其微调过程的可解释性来选择合适模型。我们在多种主流智能手机上实现并评估了XPerT，实验结果表明，该方法使手机端LLM个性化计算成本降低83%，数据效率提升51%。
原文摘要 · Abstract (English)
Personalization of Large Language Models (LLMs) is important in practical applications to accommodate the individual needs of different mobile users. Due to data privacy concerns, LLM personalization often needs to be locally done at the user's mobile device, but such on-device personalization is constrained by both the limitation of on-device compute power and insufficiency of user's personal data. In this paper, we address these constraints by fine-tuning an already personalized LLM with user's personal data, and present XPerT, a new technique that ensure proper selection of such already personalized LLMs based on explainability about how they were being fine-tuned. We implemented and evaluated XPerT on various smartphone models with mainstream LLMs, and experiment results show that XPerT reduces the computation costs of on-device LLM personalization by 83%, and improves its data efficiency by 51%.
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。