# EdgeWisePersona: A Dataset for On-Device User Profiling from Natural Language Interactions

arXiv: https://arxiv.org/abs/2505.11417 · HTML: https://mlsanity.com/paper/2505.11417/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 16 May 2025.

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs](https://mlsanity.com/paper/2502.09597/) (2025)
- [ParlAI: A Dialog Research Software Platform](https://mlsanity.com/paper/1705.06476/) (2017)
- [MNN: A Universal and Efficient Inference Engine](https://mlsanity.com/paper/2002.12418/) (2020)
- [Fast On-device LLM Inference with NPUs](https://mlsanity.com/paper/2407.05858/) (2024)
- [Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models](https://mlsanity.com/paper/2503.06027/) (2025)
- [Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective](https://mlsanity.com/paper/2410.04466/) (2024)
- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies](https://mlsanity.com/paper/2503.02891/) (2025)
- [Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework](https://mlsanity.com/paper/2109.09829/) (2021)
- [User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation](https://mlsanity.com/paper/2501.04410/) (2025)
- [Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices](https://mlsanity.com/paper/2504.08242/) (2025)
- [GenAI at the Edge: Comprehensive Survey on Empowering Edge Devices](https://mlsanity.com/paper/2502.15816/) (2025)
- [Benchmarking Edge AI Platforms for High-Performance ML Inference](https://mlsanity.com/paper/2409.14803/) (2024)
- [On-Device LLMs for Home Assistant: Dual Role in Intent Detection and Response Generation](https://mlsanity.com/paper/2502.12923/) (2025)
- [Deep Learning on Mobile Devices Through Neural Processing Units and Edge Computing](https://mlsanity.com/paper/2112.02439/) (2021)
- [Privacy-Preserving Edge Federated Learning for Intelligent Mobile-Health Systems](https://mlsanity.com/paper/2405.05611/) (2024)
- [Scaling On-Device GPU Inference for Large Generative Models](https://mlsanity.com/paper/2505.00232/) (2025)
- [Advancements in Mobile Edge Computing and Open RAN: Leveraging Artificial Intelligence and Machine Learning for Wireless Systems](https://mlsanity.com/paper/2502.02886/) (2025)
- [HE2C: A Holistic Approach for Allocating Latency-Sensitive AI Tasks across Edge-Cloud](https://mlsanity.com/paper/2411.19487/) (2024)

## Built on by (most cited first, 2 of 2)

- [PersonalHomeBench: Evaluating Agents in Personalized Smart Homes](https://mlsanity.com/paper/2604.16813/) (2026)
- [StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios](https://mlsanity.com/paper/2605.25758/) (2026)

## Abstract (arXiv)

This paper introduces a novel dataset and evaluation benchmark designed to assess and improve small language models deployable on edge devices, with a focus on user profiling from multi-session natural language interactions in smart home environments. At the core of the dataset are structured user profiles, each defined by a set of routines - context-triggered, repeatable patterns of behavior that govern how users interact with their home systems. Using these profiles as input, a large language model (LLM) generates corresponding interaction sessions that simulate realistic, diverse, and context-aware dialogues between users and their devices. The primary task supported by this dataset is profile reconstruction: inferring user routines and preferences solely from interactions history. To assess how well current models can perform this task under realistic conditions, we benchmarked several state-of-the-art compact language models and compared their performance against large foundation models. Our results show that while small models demonstrate some capability in reconstructing profiles, they still fall significantly short of large models in accurately capturing user behavior. This performance gap poses a major challenge - particularly because on-device processing offers critical advantages, such as preserving user privacy, minimizing latency, and enabling personalized experiences without reliance on the cloud. By providing a realistic, structured testbed for developing and evaluating behavioral modeling under these constraints, our dataset represents a key step toward enabling intelligent, privacy-respecting AI systems that learn and adapt directly on user-owned devices.