Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection (2504.13938v1)

Published 15 Apr 2025 in cs.HC, cs.LG, cs.AI, and cs.CL

Abstract: Personalization of 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%.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Haoming Wang (13 papers)
  2. Boyuan Yang (6 papers)
  3. Xiangyu Yin (17 papers)
  4. Wei Gao (203 papers)

Summary

We haven't generated a summary for this paper yet.