# DailyLLM: Context-Aware Activity Log Generation Using Multi-Modal Sensors and LLMs

arXiv: https://arxiv.org/abs/2507.13737 · HTML: https://mlsanity.com/paper/2507.13737/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 42 references that are in the map.
- First posted on arXiv 18 Jul 2025.

## Builds on (most cited first, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Mobile Sensor Data Anonymization](https://mlsanity.com/paper/1810.11546/) (2018)
- [Penetrative AI: Making LLMs Comprehend the Physical World](https://mlsanity.com/paper/2310.09605/) (2023)
- [HARGPT: Are LLMs Zero-Shot Human Activity Recognizers?](https://mlsanity.com/paper/2403.02727/) (2024)
- [FoodAI: Food Image Recognition via Deep Learning for Smart Food Logging](https://mlsanity.com/paper/1909.11946/) (2019)
- [IoT-LLM: a framework for enhancing Large Language Model reasoning from real-world sensor data](https://mlsanity.com/paper/2410.02429/) (2024)
- [Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Data](https://mlsanity.com/paper/2403.01133/) (2024)
- [IoT-LM: Large Multisensory Language Models for the Internet of Things](https://mlsanity.com/paper/2407.09801/) (2024)
- [When IoT Meet LLMs: Applications and Challenges](https://mlsanity.com/paper/2411.17722/) (2024)
- [Evaluation of Geographical Distortions in Language Models](https://mlsanity.com/paper/2404.17401/) (2024)

## Built on by (most cited first, 5 of 5)

- [ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild](https://mlsanity.com/paper/2512.06721/) (2025)
- [TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health](https://mlsanity.com/paper/2605.21295/) (2026)
- [SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams](https://mlsanity.com/paper/2604.06204/) (2026)
- [Listening Alone, Understanding Together: Collaborative Context Recovery for Privacy-Aware AI](https://mlsanity.com/paper/2604.13348/) (2026)
- [From 'What' to 'How' and 'Why': Sharing LLM-Generated Retrospective Summaries of Older Adults' Passive Tracking Data with Remote Family Members](https://mlsanity.com/paper/2606.03876/) (2026)

## Abstract (arXiv)

Rich and context-aware activity logs facilitate user behavior analysis and health monitoring, making them a key research focus in ubiquitous computing. The remarkable semantic understanding and generation capabilities of Large Language Models (LLMs) have recently created new opportunities for activity log generation. However, existing methods continue to exhibit notable limitations in terms of accuracy, efficiency, and semantic richness. To address these challenges, we propose DailyLLM. To the best of our knowledge, this is the first log generation and summarization system that comprehensively integrates contextual activity information across four dimensions: location, motion, environment, and physiology, using only sensors commonly available on smartphones and smartwatches. To achieve this, DailyLLM introduces a lightweight LLM-based framework that integrates structured prompting with efficient feature extraction to enable high-level activity understanding. Extensive experiments demonstrate that DailyLLM outperforms state-of-the-art (SOTA) log generation methods and can be efficiently deployed on personal computers and Raspberry Pi. Utilizing only a 1.5B-parameter LLM model, DailyLLM achieves a 17% improvement in log generation BERTScore precision compared to the 70B-parameter SOTA baseline, while delivering nearly 10x faster inference speed.