# LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis

arXiv: https://arxiv.org/abs/2604.28178 · HTML: https://mlsanity.com/paper/2604.28178/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 42 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals](https://mlsanity.com/paper/2409.00101/) (2024)
- [The Temple University Hospital Seizure Detection Corpus](https://mlsanity.com/paper/1801.08085/) (2018)
- [Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis](https://mlsanity.com/paper/2104.08336/) (2021)
- [Neuro-GPT: Towards A Foundation Model for EEG](https://mlsanity.com/paper/2311.03764/) (2023)
- [Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Models](https://mlsanity.com/paper/2211.11176/) (2022)
- [Self-Supervised Learning for Anomalous Channel Detection in EEG Graphs: Application to Seizure Analysis](https://mlsanity.com/paper/2208.07448/) (2022)
- [EEG-GPT: Exploring Capabilities of Large Language Models for EEG Classification and Interpretation](https://mlsanity.com/paper/2401.18006/) (2024)
- [BrainNet: Epileptic Wave Detection from SEEG with Hierarchical Graph Diffusion Learning](https://mlsanity.com/paper/2306.13101/) (2023)
- [Sparse Graph Learning from Spatiotemporal Time Series](https://mlsanity.com/paper/2205.13492/) (2022)
- [Graph Neural Network-based EEG Classification: A Survey](https://mlsanity.com/paper/2310.02152/) (2023)
- [Self-supervised Learning for Electroencephalogram: A Systematic Survey](https://mlsanity.com/paper/2401.05446/) (2024)
- [Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs)](https://mlsanity.com/paper/2410.07507/) (2024)
- [Data Augmentation for Seizure Prediction with Generative Diffusion Model](https://mlsanity.com/paper/2306.08256/) (2023)
- [GeoGen: A Two-stage Coarse-to-Fine Framework for Fine-grained Synthetic Location-based Social Network Trajectory Generation](https://mlsanity.com/paper/2510.07735/) (2025)
- [HealthMamba: An Uncertainty-aware Spatiotemporal Graph State Space Model for Effective and Reliable Healthcare Facility Visit Prediction](https://mlsanity.com/paper/2602.05286/) (2026)
- [Optimizing EEG Graph Structure for Seizure Detection: An Information Bottleneck and Self-Supervised Learning Approach](https://mlsanity.com/paper/2604.01595/) (2026)
- [Jensen-Shannon Divergence Message-Passing for Rich-Text Graph Representation Learning](https://mlsanity.com/paper/2512.20094/) (2025)

## Built on by (most cited first, 7 of 7)

- [EnergyMamba: An Uncertainty-Aware Graph-Enhanced Selective State Space Model for Energy Consumption Prediction](https://mlsanity.com/paper/2606.00506/) (2026)
- [NeuroGRIP: Retrieval-Augmented Graph Refinement for Knowledge-Grounded EEG Seizure Diagnosis](https://mlsanity.com/paper/2607.14314/) (2026)
- [SynEnergy: Anomaly Semantic-Guided Diffusion for Synthetic Energy Data Generation](https://mlsanity.com/paper/2608.03087/) (2026)
- [EpiGraph: Building Generalists for Evidence-Intensive Epilepsy Reasoning in the Wild](https://mlsanity.com/paper/2605.09505/) (2026)
- [SOMA: Efficient Multi-turn LLM Serving via Small Language Model](https://mlsanity.com/paper/2605.11317/) (2026)
- [SynEHR: Joint Modeling Inter-visit Temporal Evolution and Intra-visit Clinical Structure for Longitudinal EHR Synthesis](https://mlsanity.com/paper/2608.21673/) (2026)
- [Capability Scaling-Down Laws for LLM Compression](https://mlsanity.com/paper/2610.02462/) (2026)

## Abstract (arXiv)

Electroencephalogram (EEG) signals are vital for automated seizure detection, but their inherent noise makes robust representation learning challenging. Existing graph construction methods, whether correlation-based or learning-based, often generate redundant or irrelevant edges due to the noisy nature of EEG data. This significantly impairs the quality of graph representation and limits downstream task performance. Motivated by the remarkable reasoning and contextual understanding capabilities of large language models (LLMs), we explore the idea of using LLMs as graph edge refiners. Specifically, we propose a two-stage framework: we first verify that LLM-based edge refinement can effectively identify and remove redundant connections, leading to significant improvements in seizure detection accuracy and more meaningful graph structures. Building on this insight, we further develop a robust solution where the initial graph is constructed using a Transformer-based edge predictor and multilayer perceptron, assigning probability scores to potential edges and applying a threshold to determine their existence. The LLM then acts as an edge set refiner, making informed decisions based on both textual and statistical features of node pairs to validate the remaining connections. Extensive experiments on TUSZ dataset demonstrate that our LLM-refined graph learning framework not only enhances task performance but also yields cleaner and more interpretable graph representations.