Published August 11, 2025 | Version v1
Publication Open

Large Language Models in the Diagnosis of Learning Difficulties: A Brief Review and Future Directions

Authors/Creators

Description

Large Language Models (LLMs), a leading development in Artificial Intelligence (AI), are influencing education through applications such as chatbot tutors and personalized learning systems. Learning Disabilities (LDs) and neurodevelopmental conditions like ADHD and autism spectrum disorder (ASD) can significantly affect reading, writing, arithmetic, language comprehension, and concentration. Integrating LLMs into this area can assist professionals in diagnosing and supporting individuals with learning challenges. While LLMs have been widely explored for supporting people with Special Educational Needs and Disabilities (SEND), fewer studies address their potential for diagnosing and categorizing learning difficulties. This review examines the intersection of LLMs and learning disabilities, outlines current research on diagnostic applications, discusses practical considerations, and highlights future directions for inclusive implementation.

Files

LLMs in LDs.pdf

Files (816.6 kB)

Name Size Download all
md5:d5bfe17a48afeb1203f618050c210ef2
816.6 kB Preview Download

Additional details

Dates

Other
2025-08-11

References

  • Abdullah, M., & Negied, N. (2024). Detection and Prediction of Future Mental Disorder from Social Media Data Using Machine Learning, Ensemble Learning, and Large Language Models. IEEE Access, 12, 120553–120569. https://doi.org/10.1109/ACCESS.2024.3406469
  • Aggarwal, V., Thukral, S., Patel, K., & Chatterjee, A. (2024, December). Leveraging LLMs for Mental Health: Detection and Recommendations from Social Discussions. In 2024 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) (pp. 350 354). IEEE.
  • Chen, K., Lim, N., Lee, C., & Guerzhoy, M. (2024). Exploring Complex Mental Health Symptoms via Classifying Social Media Data with Explainable LLMs. arXiv preprint arXiv:2412.10414. https://doi.org/10.48550/arXiv.2412.10414
  • Chen, X.‐Y., Chen, Y.‐M., Chen, C.‐P., Su, B.‐H., Gau, S. S.‐F., & Lee, C.‐C. (2025). SocialRecNet: A Multimodal LLM-Based Framework for Assessing Social Reciprocity in Autism Spectrum Disorder. In ICASSP 2025 - IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 1–5). IEEE. https://doi.org/10.1109/ICASSP49660.2025.10888811
  • Chieffo, D. P. R., Arcangeli, V., Moriconi, F., Marfoli, A., Lino, F., Vannuccini, S., ... & Mercuri, E. M. (2023). Specific Learning Disorders (SLD) and Behavior Impairment: Comorbidity or Specific Profile? Children, 10(8), 1356. https://doi.org/10.3390/children10081356
  • Chien, Chien Wen M.D; Tai, Yueh-Ming M.D., Ph.D.. Performances of Large Language Models in Detecting Psychiatric Diagnoses from Chinese Electronic Medical Records: Comparisons between GPT-3.5, GPT-4, and GPT-4o. Taiwanese Journal of Psychiatry 38(3):p 134-141, Jul–Sep 2024. | DOI: 10.4103/TPSY.TPSY_25_24
  • Fink, N., & Fink, M. (2025). Enriching dyslexia detection with synthetic data: A comprehensive study featuring 50 old dyslexic texts and 50 new synthetic variants [Preprint]. Research Square. https://doi.org/10.21203/rs.3.rs-6074201/v1
  • Guerzhoy, M. (2024). LLMs Pick Up Cues of Potential Comorbid ADHD in People Reporting Anxiety when Keywords Are Not Enough. In AAAI 2024 Spring Symposium on Clinical Foundation Models.
  • Hoek, M. (2024). Using LLMs to extract diagnoses from clinical texts in psychiatry (Master's thesis).
  • Hongyao, H., Chun, J., Xiaoyan, G. et al. (2023). Associative gene networks reveal novel candidates important for ADHD and dyslexia comorbidity. BMC Med Genomics, 16, 208. https://doi.org/10.1186/s12920-023-01502-1
  • Hu, C., Li, W., Ruan, M., Yu, X., Paul, L. K., Wang, S., & Li, X. (2024, May 3). Exploiting ChatGPT for diagnosing autism associated language disorders and identifying distinct features [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2405.01799
  • Jiang, Y., Shen, Q., Lai, S., Qi, S., Zheng, Q., Yao, L., Wang, Y., & Pan, G. (2024). Copiloting Diagnosis of Autism in Real Clinical Scenarios via LLMs. arXiv. https://doi.org/10.48550/arXiv.2410.05684
  • Jin, H., Kim, Y., Jung, D., Kim, S., Choi, K., Son, J., & Kim, J. (2025). Investigating large language models in diagnosing students' cognitive skills in math problem solving [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2504.00843
  • Karim, A. A. J., Asad, K. H. M., & Alam, M. G. R. (2025). Larger models yield better results? Streamlined severity classification of ADHD-related concerns using BERT-based knowledge distillation. PLoS One, 20(2), e0315829.
  • Keilitz, I., & Dunivant, N. (1986). The Relationship Between Learning Disability and Juvenile Delinquency: Current State of Knowledge. Remedial and Special Education, 7(3), 18-26. https://doi.org/10.1177/074193258600700305
  • Kulkarni, A., & Prasad, J. R. (2025). Utilizing large language models for the analysis of video data in early attention deficit hyperactivity disorder detection in children. Engineered Science, 33, 1396. https://doi.org/10.30919/es8d1396
  • Mukherjee, P., Gokul, R. S., Sadhukhan, S., Godse, M., & Chakraborty, B. (2023). Detection of Autism Spectrum Disorder (ASD) from Natural Language Text using BERT and ChatGPT Models. International Journal of Advanced Computer Science and Applications, 14(10), 382–396.
  • Nguyen, Q.-T., Nguyen, H., Tang, Q.-H., Truong, T., Pham, V.-T., Le, L., & Williams-King, D. (2024). Learning disorder detection using eye tracking: Are large language models better than machine learning? In Proceedings of the ACM Symposium on Eye Tracking Research & Applications. https://doi.org/10.1145/3715669.3726785
  • Otal, H.T., Faraone, S.V., Canbaz, M.A. (2025). A New Perspective on ADHD Research: Knowledge Graph Construction with LLMs and Network Based Insights. In: Cherifi, H., Donduran, M., Rocha, L.M., Cherifi, C., Varol, O. (eds) Complex Networks & Their Applications XIII. COMPLEX NETWORKS 2024 2024. Studies in Computational Intelligence, vol 1187. Springer, Cham. https://doi.org/10.1007/978-3-031-82427-2_28
  • Phatangare, S., Jain, S., Chakrabarty, S., Chougule, S., & Bisen, S. (2025). LexiEase AI: An AI-powered dyslexic support system. In 2025 5th International Conference on Trends in Material Science and Inventive Materials (ICTMIM) (pp. 1412–1417). IEEE. https://doi.org/10.1109/ICTMIM65579.2025.10987997
  • Schmidt, L. T. (2023). Predicting psychological disorders via Twitter data and large language models (Bachelor's thesis). Eindhoven University of Technology. https://pure.tue.nl/ws/portalfiles/portal/341713180/Thesis_BDS_Lukas_Schmidt.pdf
  • Settanni, M., Quilghini, F., Toscano, A., & Marengo, D. (2025). Assessing the accuracy and consistency of large language models in triaging social media posts for psychological distress. Psychiatry Research, 351, 116583. https://doi.org/10.1016/j.psychres.2025.116583
  • Shan, Y., Li, X., Wang, J., & Chen, H. (2025). Comparing diagnostic accuracy of clinical professionals and large language models: Systematic review and meta-analysis. Journal of Medical Internet Research, 27(1), e64963. https://doi.org/10.2196/64963
  • Sharma, P., Agarwal, B., Yadav, G.S. et al. (2025). Vision transformer-based model for early detection of dysgraphia among school students. Microsyst Technol, 31, 775–785. https://doi.org/10.1007/s00542-024-05741-9
  • Wiechmann, D., Kempa, E., Kerz, E., & Qiao, Y. (2024). Transparent but Powerful: Explainability, Accuracy, and Generalizability in ADHD Detection from Social Media Data. arXiv preprint arXiv:2411.15586.
  • Zhang, Y., Li, Y., Wang, X., & Zhang, H. (2024). In Proceedings of the ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (pp. 1–8). https://doi.org/10.1145/3698587.3701538
  • Zhu, Y., Guo, Y., Marchuck, N., Sarker, A., & Wang, Y. (2025, May 27). Leveraging large language models and traditional machine learning ensembles for ADHD detection from narrative transcripts. arXiv preprint arXiv:2505.21324. https://doi.org/10.48550/arXiv.2505.21324