EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

YUNet_LLMClaimReport: An Enhanced Automobile Insurance Fraud Detection and Automated Claim Report Generation Using Large Language Models

P. Anand Kumar, S. Sountharrajan

IEEE Access · 2025 · 13 · 121935-121954

DOI: 10.1109/access.2025.3584927 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von P. Anand Kumar und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The detection of fraud in automobile insurance and processing of automobile claims are still a challenge since manual inspections are carried out and automated systems are fragmented. The state-of-the-art approaches (convolutional neural networks, statistical models, etc.) tend to focus on separate tasks (damage detection, fraud classification, etc.), without being integrated with report generation on an end-to-end basis, and without making sufficient use of unstructured information (e.g., images, claim descriptions). In this research, YUNet_LLMClaimReport, a new framework is proposed that combines YOLOv11, U-Net, and a fine-tuned GPT-3.5-turbo large language model to automatically generate claim reports based on the detections and segmentation. The model is trained on a custom dataset of 4,000 vehicle images within the Egyptian insurance market (70:20:10 training, validation and test split), using data augmentation, dropout (0.3) and L2 regularisation (l =0.01) to ensure robustness. The evaluation measures are mean average precision (mAP50: 0.9424), intersection over union (IoU: 0.85), claim report accuracy (CRA: 0.92+/−0.008), BLEU (0.85+/−0.01), and ROUGE-L (0.82+/−0.01). The framework runs at 8.3 FPS on NVIDIA Jetson Nano and saves processing time by 60 percent. Weaknesses are single-run measures because of computational limitations and factual inconsistencies in reports (10%). The model can be generalized to the Kaggle Car Damage Detection dataset (mAP50: 0.90), providing a scalable solution to insurance processes. The code and sample data are open sourced.

Zitieren

APA

Kumar, P. A., & Sountharrajan, S. (2025). YUNet_LLMClaimReport: An Enhanced Automobile Insurance Fraud Detection and Automated Claim Report Generation Using Large Language Models. IEEE Access, 13, 121935-121954. https://doi.org/10.1109/access.2025.3584927

Vancouver

Kumar PA, Sountharrajan S. YUNet_LLMClaimReport: An Enhanced Automobile Insurance Fraud Detection and Automated Claim Report Generation Using Large Language Models. IEEE Access. 2025;13:121935-121954. doi:10.1109/access.2025.3584927

BibTeX
@article{Kumar2025,
  author = {Kumar, P. Anand and Sountharrajan, S.},
  title = {YUNet_LLMClaimReport: An Enhanced Automobile Insurance Fraud Detection and Automated Claim Report Generation Using Large Language Models},
  journal = {IEEE Access},
  year = {2025},
  volume = {13},
  pages = {121935--121954},
  doi = {10.1109/access.2025.3584927}
}
Kostenlos starten →