Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection

• URL: http://arxiv.org/abs/2504.13938v1
• Date: Tue, 15 Apr 2025 17:38:06 GMT
• Title: Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection
• Authors: Haoming Wang, Boyuan Yang, Xiangyu Yin, Wei Gao,
• Abstract summary: Personalization of Large Language Models (LLMs) is important in practical applications to accommodate the individual needs of different mobile users.<n>We present XPerT, a new technique that ensure proper selection of such already personalized LLMs based on explainability about how they were being fine-tuned.<n>Experiment results show that XPerT reduces the costs of on-device LLM personalization by 83%, and improves its data efficiency by 51%.
• Score: 5.174560360759384
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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%.

Related papers

• CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering [68.91862701376155]
  CoSteer is a novel collaborative framework that enables decoding-time personalization through localized delta steering.<n>We formulate token-level optimization as an online learning problem, where local delta vectors dynamically adjust the remote LLM's logits.<n>This approach preserves privacy by transmitting only the final steered tokens rather than raw data or intermediate vectors.
  arXiv  Detail & Related papers  (2025-07-07T08:32:29Z)
• Personalized Language Models via Privacy-Preserving Evolutionary Model Merging [57.161917758405465]
  Personalization in large language models (LLMs) seeks to tailor models to individual user or user group preferences.<n>We propose Privacy-Preserving Model Merging via Evolutionary Algorithms (PriME)<n>PriME employs gradient-free methods to directly optimize task-specific metrics while preserving user privacy.
  arXiv  Detail & Related papers  (2025-03-23T09:46:07Z)
• Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices [16.500721672193762]
  Large Language Models (LLMs) can be adapted to specialized domains using private datasets stored on resource-constrained edge devices. We propose Prada, a privacy-preserving and efficient black-box LLM adaptation system using private on-device datasets. Prada achieves performance comparable to centralized fine-tuning methods while significantly reducing computational overhead by up to 60% and communication costs by up to 80%.
  arXiv  Detail & Related papers  (2025-03-19T06:38:51Z)
• Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization [68.79814761867314]
  We propose Difference-aware Personalization Learning (DPL) to enhance Large Language Models (LLMs) personalization.<n>DPL strategically selects representative users for comparison and establishes a structured standard to extract task-relevant differences.<n>Experiments on real-world datasets demonstrate that DPL significantly enhances LLM personalization.
  arXiv  Detail & Related papers  (2025-03-04T09:53:26Z)
• Personalize Your LLM: Fake it then Align it [12.436528089142698]
  CHAMELEON is a scalable and efficient personalization approach that uses self-generated personal preference data and representation editing.<n>Our experiments show that CHAMELEON efficiently adapts models to personal preferences, improving instruction-tuned models and outperforms two personalization baselines by an average of 40%.
  arXiv  Detail & Related papers  (2025-03-02T22:40:10Z)
• FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users [111.56469697145519]
  We propose Few-Shot Preference Optimization, which reframes reward modeling as a meta-learning problem.<n>Under this framework, an LLM learns to quickly adapt to a user via a few labeled preferences from that user, constructing a personalized reward function for them.<n>We generate over 1M synthetic personalized preferences using publicly available LLMs.<n>We evaluate FSPO on personalized open-ended generation for up to 1,500 synthetic users across three domains: movie reviews, pedagogical adaptation based on educational background, and general question answering, along with a controlled human study.
  arXiv  Detail & Related papers  (2025-02-26T17:08:46Z)
• Personalization of Large Language Models: A Survey [131.00650432814268]
  Personalization of Large Language Models (LLMs) has recently become increasingly important with a wide range of applications. Most existing works on personalized LLMs have focused either entirely on (a) personalized text generation or (b) leveraging LLMs for personalization-related downstream applications, such as recommendation systems. We introduce a taxonomy for personalized LLM usage and summarizing the key differences and challenges.
  arXiv  Detail & Related papers  (2024-10-29T04:01:11Z)
• LLMs + Persona-Plug = Personalized LLMs [41.60364110693824]
  Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs based on their individual interests. This has led to the development of various personalized approaches aimed at adapting large language models (LLMs) to generate customized outputs aligned with user preferences. We propose a novel personalized LLM model, ours. It constructs a user-specific embedding for each individual by modeling all her historical contexts through a lightweight plug-in user embedder module.
  arXiv  Detail & Related papers  (2024-09-18T11:54:45Z)
• Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation [50.837277466987345]
  We focus on the field of large language models (LLMs) for recommendation. We propose RecLoRA, which incorporates a Personalized LoRA module that maintains independent LoRAs for different users. We also design a Few2Many Learning Strategy, using a conventional recommendation model as a lens to magnify small training spaces to full spaces.
  arXiv  Detail & Related papers  (2024-08-07T04:20:28Z)
• PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs [5.063806958859058]
  On mobile devices, the wealth of valuable, non-public data generated daily holds great promise for locally fine-tuning personalized LLMs. We propose employing derivative-free optimization techniques to enable on-device fine-tuning of LLM, even on memory-limited mobile devices. Empirical results demonstrate that the RoBERTa-large model and OPT-1.3B can be fine-tuned locally on the OPPO Reno 6 smartphone using around 4GB and 6.5GB of memory respectively.
  arXiv  Detail & Related papers  (2024-07-01T07:26:56Z)
• ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning [95.64041188351393]
  This paper endeavors to solve both the challenges of limited resources and personalization. We propose a method named ZOOPFL that uses Zeroth-Order Optimization for Personalized Federated Learning. To reduce the computation costs and enhance personalization, we propose input surgery to incorporate an auto-encoder with low-dimensional and client-specific embeddings.
  arXiv  Detail & Related papers  (2023-10-08T12:26:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.