# Peak-Detector: Explainable Peak Detection via Instruction-Tuned Large Language Models in Physiological Sign

arXiv: https://arxiv.org/abs/2605.16452 · HTML: https://mlsanity.com/paper/2605.16452/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 81 references that are in the map.
- First posted on arXiv 15 May 2026.

## Builds on (most cited first, 14 of 14)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI](https://mlsanity.com/paper/1907.07374/) (2019)
- [Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmark](https://mlsanity.com/paper/2404.16563/) (2024)
- [CardioGAN: Attentive Generative Adversarial Network with Dual Discriminators for Synthesis of ECG from PPG](https://mlsanity.com/paper/2010.00104/) (2020)
- [Apple Intelligence Foundation Language Models: Tech Report 2025](https://mlsanity.com/paper/2507.13575/) (2025)
- [Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Models](https://mlsanity.com/paper/2505.24187/) (2025)
- [LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods](https://mlsanity.com/paper/2407.00322/) (2024)
- [RPnet: A Deep Learning approach for robust R Peak detection in noisy ECG](https://mlsanity.com/paper/2004.08103/) (2020)
- [Beyond A Single AI Cluster: A Survey of Decentralized LLM Training](https://mlsanity.com/paper/2503.11023/) (2025)
- [Sustainable AI Training via Hardware-Software Co-Design on NVIDIA, AMD, and Emerging GPU Architectures](https://mlsanity.com/paper/2508.13163/) (2025)

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

- [DynamicDx: Evaluating Evidence Acquisition in Video-Based Diagnosis](https://mlsanity.com/paper/2609.32957/) (2026)

## Abstract (arXiv)

Accurate peak detection across diverse cardiac physiological signals, including the Electrocardiogram (ECG), Photoplethysmogram (PPG), Ballistocardiogram (BCG), and Bodyseismography (BSG), is fundamental for cardiovascular monitoring but is often hindered by artifacts and signal variability. Conventional algorithms are typically engineered with expert knowledge for a single signal modality, limiting their generalizability. Conversely, deep learning-based methods often lack interpretability, limiting transparency for expert verification and hindering expert-computer interaction. To address these limitations, we introduce Peak-Detector, a novel framework that leverages instruction-tuned Large Language Models (LLMs) for robust, cross-modal, and explainable peak detection. A core innovation of our framework is a "peak-representation" technique that transforms time-series data into a condensed format, preserving critical event information while significantly reducing signal length. This representation provides a crucial inductive bias, guiding the LLM to reason over physiologically meaningful events rather than raw, noisy data. The model is optimized through a two-stage process: supervised fine-tuning (SFT) followed by reinforcement learning (RL) with a multi-objective reward function. The model's self-explanation capabilities are cultivated by fine-tuning on a custom-built Peak-Explanation dataset. Across four modalities-ECG, PPG, BCG, and BSG-spanning seven datasets (six public benchmarks plus one real-world cohort), Peak-Detector demonstrates strong cross-modal performance, achieving best or tied-best detection under clinically relevant temporal tolerance. Beyond accuracy, the generated rationales surface failure modes and support verification and error analysis.