# Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection

arXiv: https://arxiv.org/abs/2505.18754 · HTML: https://mlsanity.com/paper/2505.18754/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 46 references that are in the map.
- First posted on arXiv 24 May 2025.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [True Few-Shot Learning with Language Models](https://mlsanity.com/paper/2105.11447/) (2021)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [Noisy Channel Language Model Prompting for Few-Shot Text Classification](https://mlsanity.com/paper/2108.04106/) (2021)
- [Large Language Models are Few-Shot Health Learners](https://mlsanity.com/paper/2305.15525/) (2023)
- [A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models](https://mlsanity.com/paper/2110.08484/) (2021)
- [In-Context Learning with Iterative Demonstration Selection](https://mlsanity.com/paper/2310.09881/) (2023)
- [Active Learning Principles for In-Context Learning with Large Language Models](https://mlsanity.com/paper/2305.14264/) (2023)
- [Skill-Based Few-Shot Selection for In-Context Learning](https://mlsanity.com/paper/2305.14210/) (2023)
- [SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition](https://mlsanity.com/paper/2410.10624/) (2024)
- [The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models](https://mlsanity.com/paper/2309.06236/) (2023)
- [On Training Instance Selection for Few-Shot Neural Text Generation](https://mlsanity.com/paper/2107.03176/) (2021)
- [Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Data](https://mlsanity.com/paper/2403.01133/) (2024)
- [Few-Shot Learning-Based Human Activity Recognition](https://mlsanity.com/paper/1903.10416/) (2019)
- [Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification](https://mlsanity.com/paper/2410.10756/) (2024)
- [Knowledge Prompting for Few-shot Action Recognition](https://mlsanity.com/paper/2211.12030/) (2022)
- [Automatic Combination of Sample Selection Strategies for Few-Shot Learning](https://mlsanity.com/paper/2402.03038/) (2024)
- [Designing Informative Metrics for Few-Shot Example Selection](https://mlsanity.com/paper/2403.03861/) (2024)
- [Selecting Shots for Demographic Fairness in Few-Shot Learning with Large Language Models](https://mlsanity.com/paper/2311.08472/) (2023)

## Built on by (most cited first, 1 of 1)

- [LLM-Guided Exemplar Selection for Few-Shot Wearable-Sensor Human Activity Recognition](https://mlsanity.com/paper/2512.22385/) (2025)

## Abstract (arXiv)

In this paper, we propose a novel few-shot optimization with HED-LM (Hybrid Euclidean Distance with Large Language Models) to improve example selection for sensor-based classification tasks. While few-shot prompting enables efficient inference with limited labeled data, its performance largely depends on the quality of selected examples. HED-LM addresses this challenge through a hybrid selection pipeline that filters candidate examples based on Euclidean distance and re-ranks them using contextual relevance scored by large language models (LLMs). To validate its effectiveness, we apply HED-LM to a fatigue detection task using accelerometer data characterized by overlapping patterns and high inter-subject variability. Unlike simpler tasks such as activity recognition, fatigue detection demands more nuanced example selection due to subtle differences in physiological signals. Our experiments show that HED-LM achieves a mean macro F1-score of 69.13±10.71%, outperforming both random selection (59.30±10.13%) and distance-only filtering (67.61±11.39%). These represent relative improvements of 16.6% and 2.3%, respectively. The results confirm that combining numerical similarity with contextual relevance improves the robustness of few-shot prompting. Overall, HED-LM offers a practical solution to improve performance in real-world sensor-based learning tasks and shows potential for broader applications in healthcare monitoring, human activity recognition, and industrial safety scenarios.