Reliable interpretation of multimodal data in dentistry is essential for automated oral healthcare, yet current multimodal large language models (MLLMs) struggle to capture fine-grained dental visual details and lack sufficient reasoning ability for precise diagnosis. To address these limitations, we present DentalGPT, a specialized dental MLLM developed through high-quality domain knowledge injection and reinforcement learning. Specifically, the largest annotated multimodal dataset for dentistry to date was constructed by aggregating over 120k dental images paired with detailed descriptions that highlight diagnostically relevant visual features, making it the multimodal dataset with the most extensive collection of dental images to date. Training on this dataset significantly enhances the MLLM's visual understanding of dental conditions, while the subsequent reinforcement learning stage further strengthens its capability for multimodal complex reasoning. Comprehensive evaluations on intraoral and panoramic benchmarks, along with dental subsets of medical VQA benchmarks, show that DentalGPT achieves superior performance in disease classification and dental VQA tasks, outperforming many state-of-the-art MLLMs despite having only 7B parameters. These results demonstrate that high-quality dental data combined with staged adaptation provides an effective pathway for building capable and domain-specialized dental MLLMs.
@article{arxiv.2512.11558,
title = {DentalGPT: Incentivizing Multimodal Complex Reasoning in Dentistry},
author = {Zhenyang Cai and Jiaming Zhang and Junjie Zhao and Ziyi Zeng and Yanchao Li and Jingyi Liang and Junying Chen and Yunjin Yang and Jiajun You and Shuzhi Deng and Tongfei Wang and Wanting Chen and Chunxiu Hao and Ruiqi Xie and Zhenwei Wen and Xiangyi Feng and Zou Ting and Jin Zou Lin and Jianquan Li and Guangjun Yu and Liangyi Chen and Junwen Wang and Shan Jiang and Benyou Wang},
journal= {arXiv preprint arXiv:2512.11558},
year = {2025}
}