# DeepFeature: LLM-Empowered Context-aware Feature Generation for Wearable Biosignals

arXiv: https://arxiv.org/abs/2512.08379 · HTML: https://mlsanity.com/paper/2512.08379/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 79 references that are in the map.
- First posted on arXiv 9 Dec 2025.

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

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification](https://mlsanity.com/paper/2012.08791/) (2020)
- [Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering](https://mlsanity.com/paper/2305.03403/) (2023)
- [catch22: CAnonical Time-series CHaracteristics](https://mlsanity.com/paper/1901.10200/) (2019)
- [Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning](https://mlsanity.com/paper/2404.09491/) (2024)
- [Feature Engineering for Predictive Modeling using Reinforcement Learning](https://mlsanity.com/paper/1709.07150/) (2017)
- [The autofeat Python Library for Automated Feature Engineering and Selection](https://mlsanity.com/paper/1901.07329/) (2019)
- [Limitations of Language Models in Arithmetic and Symbolic Induction](https://mlsanity.com/paper/2208.05051/) (2022)
- [LMPriors: Pre-Trained Language Models as Task-Specific Priors](https://mlsanity.com/paper/2210.12530/) (2022)
- [OpenFE: Automated Feature Generation with Expert-level Performance](https://mlsanity.com/paper/2211.12507/) (2022)
- [Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning](https://mlsanity.com/paper/2406.08527/) (2024)
- [AutoDS: Towards Human-Centered Automation of Data Science](https://mlsanity.com/paper/2101.05273/) (2021)
- [Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals](https://mlsanity.com/paper/2412.09758/) (2024)
- [Self-optimizing Feature Generation via Categorical Hashing Representation and Hierarchical Reinforcement Crossing](https://mlsanity.com/paper/2309.04612/) (2023)
- [Evolutionary Large Language Model for Automated Feature Transformation](https://mlsanity.com/paper/2405.16203/) (2024)
- [Dynamic and Adaptive Feature Generation with LLM](https://mlsanity.com/paper/2406.03505/) (2024)
- [Exploring Large Language Models for Feature Selection: A Data-centric Perspective](https://mlsanity.com/paper/2408.12025/) (2024)
- [DrHouse: An LLM-empowered Diagnostic Reasoning System through Harnessing Outcomes from Sensor Data and Expert Knowledge](https://mlsanity.com/paper/2405.12541/) (2024)
- [AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications](https://mlsanity.com/paper/2503.05346/) (2025)
- [Interpreting Deep Learning Features for Myoelectric Control: A Comparison with Handcrafted Features](https://mlsanity.com/paper/1912.00283/) (2019)
- [Language Models are Symbolic Learners in Arithmetic](https://mlsanity.com/paper/2410.15580/) (2024)
- [OpenTCM: A GraphRAG-Empowered LLM-based System for Traditional Chinese Medicine Knowledge Retrieval and Diagnosis](https://mlsanity.com/paper/2504.20118/) (2025)
- [A Survey of Few-Shot Learning for Biomedical Time Series](https://mlsanity.com/paper/2405.02485/) (2024)
- [SMARTFEAT: Efficient Feature Construction through Feature-Level Foundation Model Interactions](https://mlsanity.com/paper/2309.07856/) (2023)
- [Leveraging Large Language Models for Generating Mobile Sensing Strategies in Human Behavior Modeling](https://mlsanity.com/paper/2311.05457/) (2023)
- [PREPRINT: Comparison of deep learning and hand crafted features for mining simulation data](https://mlsanity.com/paper/2103.06552/) (2021)
- [SensEmo: Enabling Affective Learning through Real-time Emotion Recognition with Smartwatches](https://mlsanity.com/paper/2407.09911/) (2024)

## Abstract (arXiv)

Biosignals collected from wearable devices are widely utilized in healthcare applications. Machine learning models used in these applications often rely on features extracted from biosignals due to their effectiveness, lower data dimensionality, and wide compatibility across various model architectures. However, existing feature extraction methods often lack task-specific contextual knowledge, struggle to identify optimal features in high-dimensional combinatorial feature space, and are prone to automated code generation and execution errors. In this paper, we propose DeepFeature, the first LLM-empowered, context-aware feature generation framework for wearable biosignals. DeepFeature introduces a multi-source feature generation mechanism that integrates the inherent ability of LLMs, expert knowledge and inter-feature interactions. It also employs an iterative feature refinement process that uses feature assessment-based feedback for feature re-selection. Additionally, DeepFeature utilizes a robust multi-layer filtering and verification approach for feature description-to-code translation to ensure that the feature extraction functions run without crashing. Experimental evaluation results show that DeepFeature achieves the highest average AUROC across eight tasks under both sample-level and subject-level settings, outperforming the best baselines by 4.60% and 4.61%, respectively. DeepFeature achieves the most pronounced gains on the PPG-BP tasks, while remaining competitive with the best-performing baselines on Epilepsy, WESAD, and our self-collected SEN dataset.