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

• URL: http://arxiv.org/abs/2505.11417v1
• Date: Fri, 16 May 2025 16:29:21 GMT
• Title: EdgeWisePersona: A Dataset for On-Device User Profiling from Natural Language Interactions
• Abstract summary: This paper introduces a novel dataset designed to assess and improve small language models deployable on edge devices.<n>At the core of the dataset are structured user profiles, each defined by a set of routines.<n>A large language model (LLM) generates corresponding interaction sessions that simulate realistic, diverse, and context-aware dialogues.
• Score: 0.6650227510403052
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions [63.13827503828231]
  We introduce VitaBench 2.0, a benchmark for evaluating personalized and proactive agent behavior in long-term user interactions.<n>Results show that real-world personalization remains highly challenging even for state-of-the-art models.
  arXiv  Detail & Related papers  (2026-05-26T15:07:38Z)
• The Model Is Not the Product: A Dual-Pillar Architecture for Local-First Psychological Coaching [51.56484100374058]
  This report introduces Psych LM, an iOS application that validates the thesis that, for such applications, the surrounding architecture is paramount.<n>Psych LM runs a local, on-device language model within a purpose-built, local-first runtime designed for behavioral and life-coaching applications.
  arXiv  Detail & Related papers  (2026-05-23T05:49:11Z)
• PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments [72.02445514666428]
  We introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall.<n>PerMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time.<n> Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption.
  arXiv  Detail & Related papers  (2026-03-24T14:04:11Z)
• Synthetic Interaction Data for Scalable Personalization in Large Language Models [67.31884245564086]
  We introduce a high-fidelity synthetic data generation framework called PersonaGym.<n>Unlike prior work that treats personalization as static persona-preference pairs, PersonaGym models a dynamic preference process.<n>We release PersonaAtlas, a large-scale, high-quality, and diverse synthetic dataset of high-fidelity multi-turn personalized interaction trajectories.
  arXiv  Detail & Related papers  (2026-02-12T20:41:22Z)
• Personalized Vision via Visual In-Context Learning [62.85784251383279]
  We present a visual in-context learning framework for personalized vision.<n>PICO infers the underlying transformation and applies it to new inputs without retraining.<n>We also propose an attention-guided seed scorer that improves reliability via efficient inference scaling.
  arXiv  Detail & Related papers  (2025-09-29T17:58:45Z)
• Personas within Parameters: Fine-Tuning Small Language Models with Low-Rank Adapters to Mimic User Behaviors [1.8352113484137629]
  A long-standing challenge in developing accurate recommendation models is simulating user behavior, mainly due to the complex nature of user interactions.<n>We propose an approach to extracting robust user representations using a frozen Large Language Models (LLMs) and simulating cost-effective, resource-efficient user agents powered by fine-tuned Small Language Models (SLMs)<n>Our experiments provide compelling empirical evidence of the efficacy of our methods, demonstrating that user agents developed using our approach have the potential to bridge the gap between offline metrics and real-world performance of recommender systems.
  arXiv  Detail & Related papers  (2025-08-18T22:14:57Z)
• ASMR: Augmenting Life Scenario using Large Generative Models for Robotic Action Reflection [21.75681306780917]
  This paper introduces a novel framework focusing on data augmentation in robotic assistance scenarios.<n>It involves leveraging a sophisticated large language model to simulate potential conversations and environmental contexts.<n>The additionally generated data serves to refine the latest multimodal models, enabling them to more accurately determine appropriate actions.
  arXiv  Detail & Related papers  (2025-06-16T19:58:54Z)
• PersonaAgent: When Large Language Model Agents Meet Personalization at Test Time [87.99027488664282]
  PersonaAgent is a framework designed to address versatile personalization tasks.<n>It integrates a personalized memory module and a personalized action module.<n>Test-time user-preference alignment strategy ensures real-time user preference alignment.
  arXiv  Detail & Related papers  (2025-06-06T17:29:49Z)
• Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles [37.43150003866563]
  User simulators are crucial for replicating human interactions with dialogue systems.<n>We propose User Simulator with implicit Profiles (USP), a framework that infers implicit user profiles from human-machine conversations.<n>USP outperforms strong baselines in terms of authenticity and diversity while achieving comparable performance in consistency.
  arXiv  Detail & Related papers  (2025-02-26T09:26:54Z)
• Can foundation models actively gather information in interactive environments to test hypotheses? [56.651636971591536]
  We introduce a framework in which a model must determine the factors influencing a hidden reward function.<n>We investigate whether approaches such as self- throughput and increased inference time improve information gathering efficiency.
  arXiv  Detail & Related papers  (2024-12-09T12:27:21Z)
• How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics [49.9329723199239]
  We propose a method for the automated creation of a challenging test set without relying on the manual construction of artificial and unrealistic examples. We categorize the test set of popular NLI datasets into three difficulty levels by leveraging methods that exploit training dynamics. When our characterization method is applied to the training set, models trained with only a fraction of the data achieve comparable performance to those trained on the full dataset.
  arXiv  Detail & Related papers  (2024-10-04T13:39:21Z)
• Corpus Considerations for Annotator Modeling and Scaling [9.263562546969695]
  We show that the commonly used user token model consistently outperforms more complex models. Our findings shed light on the relationship between corpus statistics and annotator modeling performance.
  arXiv  Detail & Related papers  (2024-04-02T22:27:24Z)
• CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following [27.22804560751958]
  We propose a collaborative generation framework integrating large (hosted on cloud infrastructure) and small models (deployed on local devices) to address privacy concerns logically. Our experimental findings, based on our synthesized dataset and two additional open-source datasets, indicate that: 1) Large-scale models perform well when provided with user context but struggle in the absence of such context. Our framework, utilizing mixed-scale models, showcases competitive performance, providing a feasible solution to privacy issues.
  arXiv  Detail & Related papers  (2024-03-05T17:15:28Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• Federated Privacy-preserving Collaborative Filtering for On-Device Next App Prediction [52.16923290335873]
  We propose a novel SeqMF model to solve the problem of predicting the next app launch during mobile device usage. We modify the structure of the classical matrix factorization model and update the training procedure to sequential learning. One more ingredient of the proposed approach is a new privacy mechanism that guarantees the protection of the sent data from the users to the remote server.
  arXiv  Detail & Related papers  (2023-02-05T10:29:57Z)
• On-device modeling of user's social context and familiar places from smartphone-embedded sensor data [7.310043452300736]
  We propose a novel, unsupervised and lightweight approach to model the user's social context and her locations. We exploit data related to both physical and cyber social interactions among users and their devices. We show the performance of 3 machine learning algorithms to recognize daily-life situations.
  arXiv  Detail & Related papers  (2022-05-18T08:32:26Z)
• RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems [75.87418236410296]
  We introduce the RADDLE benchmark, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. RADDLE is designed to favor and encourage models with a strong generalization ability. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain.
  arXiv  Detail & Related papers  (2020-12-29T08:58:49Z)

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.