# AI-Generated Fall Data: Assessing LLMs and Diffusion Model for Wearable Fall Detection

arXiv: https://arxiv.org/abs/2505.04660 · HTML: https://mlsanity.com/paper/2505.04660/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 27 of its 55 references that are in the map.
- First posted on arXiv 7 May 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 27 of 27)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024)
- [Does Synthetic Data Generation of LLMs Help Clinical Text Mining?](https://mlsanity.com/paper/2303.04360/) (2023)
- [Large Language Models are Few-Shot Health Learners](https://mlsanity.com/paper/2305.15525/) (2023)
- [Where Would I Go Next? Large Language Models as Human Mobility Predictors](https://mlsanity.com/paper/2308.15197/) (2023)
- [Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression](https://mlsanity.com/paper/2411.16575/) (2024)
- [Penetrative AI: Making LLMs Comprehend the Physical World](https://mlsanity.com/paper/2310.09605/) (2023)
- [ParCo: Part-Coordinating Text-to-Motion Synthesis](https://mlsanity.com/paper/2403.18512/) (2024)
- [ElderSim: A Synthetic Data Generation Platform for Human Action Recognition in Eldercare Applications](https://mlsanity.com/paper/2010.14742/) (2020)
- [M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models](https://mlsanity.com/paper/2407.14502/) (2024)
- [SATO: Stable Text-to-Motion Framework](https://mlsanity.com/paper/2405.01461/) (2024)
- [Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition](https://mlsanity.com/paper/2305.03187/) (2023)
- [MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks](https://mlsanity.com/paper/2411.19786/) (2024)
- [Using Pretrained Large Language Model with Prompt Engineering to Answer Biomedical Questions](https://mlsanity.com/paper/2407.06779/) (2024)
- [Creating a Large-scale Synthetic Dataset for Human Activity Recognition](https://mlsanity.com/paper/2007.11118/) (2020)
- [On the Benefit of Generative Foundation Models for Human Activity Recognition](https://mlsanity.com/paper/2310.12085/) (2023)
- [Fall Detection using Knowledge Distillation Based Long short-term memory for Offline Embedded and Low Power Devices](https://mlsanity.com/paper/2308.12481/) (2023)

## Abstract (arXiv)

Training fall detection systems is challenging due to the scarcity of real-world fall data, particularly from elderly individuals. To address this, we explore the potential of Large Language Models (LLMs) for generating synthetic fall data. This study evaluates text-to-motion (T2M, SATO, ParCo) and text-to-text models (GPT4o, GPT4, Gemini) in simulating realistic fall scenarios. We generate synthetic datasets and integrate them with four real-world baseline datasets to assess their impact on fall detection performance using a Long Short-Term Memory (LSTM) model. Additionally, we compare LLM-generated synthetic data with a diffusion-based method to evaluate their alignment with real accelerometer distributions. Results indicate that dataset characteristics significantly influence the effectiveness of synthetic data, with LLM-generated data performing best in low-frequency settings (e.g., 20Hz) while showing instability in high-frequency datasets (e.g., 200Hz). While text-to-motion models produce more realistic biomechanical data than text-to-text models, their impact on fall detection varies. Diffusion-based synthetic data demonstrates the closest alignment to real data but does not consistently enhance model performance. An ablation study further confirms that the effectiveness of synthetic data depends on sensor placement and fall representation. These findings provide insights into optimizing synthetic data generation for fall detection models.