Bridging the Medical Knowledge Gap

4-bit QLoRA Fine-Tuning of Llama-3-8B for Biomedical Reasoning

Authors

  • Aditya Verma Independent Researcher

DOI:

https://doi.org/10.5195/pur.2026.166

Keywords:

Artificial Intelligence, Large Language Models, Clinical Reasoning

Abstract

Large language models (LLMs) show promise for biomedical reasoning, but the compute needed to adapt them keeps this work out of reach for many researchers. This study examines whether Meta Llama-3-8B can be adapted for biomedical reasoning on a single NVIDIA T4 GPU (16 GB VRAM) using 4-bit NormalFloat (NF4) quantization and quantized low-rank adaptation (QLoRA). The adapted model, named Bio-Llama-3-Expert, was fine-tuned on the Medical-O1-Reasoning-SFT dataset with approximately 42 million trainable parameters (0.52% of the model) and evaluated on two small, study-level sets. On a 50-question PubMedQA subset (YES/NO/MAYBE), it reached 72.0% accuracy (36/50; 95% CI, 58.3–82.5%), compared with a 42.0% majority-class rate in that subset and a reported 45% for untuned Llama-3-8B with naive prompting. On a separate 69-question reasoning-complexity set, overall accuracy was 79.7% (55/69) and declined from 92.0% on direct-recall questions to 65.0% on multi-hop questions. The MAYBE class was the weakest (3 of 9 correct). The study is limited by small evaluation sets, short training runs, baseline comparisons that are not paired, and the absence of clinical validation. The results are therefore preliminary evidence of computational feasibility, not of clinical readiness.

Author Biography

Aditya Verma, Independent Researcher

Aditya Verma is a computer applications student at Lovely Professional University interested in AI, machine learning, and applying technology to solve real-world problems at the intersection of biology and computing.

References

Alsentzer, Emily, John Murphy, William Boag, Wei-Hung Weng, Di Jin, Tristan Naumann, and Matthew McDermott. 2019. “Publicly Available Clinical BERT Embeddings.” In Proceedings of the 2nd Clinical Natural Language Processing Workshop, 72–78. Association for Computational Linguistics. https://doi.org/10.18653/v1/W19-1909.

Brown, Tom B., Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, et al. 2020. “Language Models Are Few-Shot Learners.” Advances in Neural Information Processing Systems 33: 1877–1901.

Chen, Junying, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, Jianye Hou, and Benyou Wang. 2024. “HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs.” arXiv:2412.18925. Preprint, arXiv. https://arxiv.org/abs/2412.18925.

Dettmers, Tim, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. “QLoRA: Efficient Finetuning of Quantized LLMs.” Advances in Neural Information Processing Systems 36. https://arxiv.org/abs/2305.14314.

Devlin, Jacob, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. “BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding.” In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, 4171–86. Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1423.

FreedomIntelligence. 2024. Medical-O1-Reasoning-SFT. Dataset. Hugging Face. https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT.

Friedman, Carol, Philip O. Alderson, John H. M. Austin, James J. Cimino, and Stephen B. Johnson. 1994. “A General Natural-Language Text Processor for Clinical Radiology.” Journal of the American Medical Informatics Association 1 (2): 161–74. https://doi.org/10.1136/jamia.1994.95236146.

Hu, Edward J., Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. “LoRA: Low-Rank Adaptation of Large Language Models.” arXiv:2106.09685. Preprint, arXiv. https://arxiv.org/abs/2106.09685.

Jin, Qiao, Bhuwan Dhingra, Zhengping Liu, William W. Cohen, and Xinghua Lu. 2019. “PubMedQA: A Dataset for Biomedical Research Question Answering.” In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2567–77. Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1259.

Lee, Jinhyuk, Wonjin Yoon, Sungdong Kim, Donghyeon Kim, Sunkyu Kim, Chan Ho So, and Jaewoo Kang. 2020. “BioBERT: A Pre-Trained Biomedical Language Representation Model for Biomedical Text Mining.” Bioinformatics 36 (4): 1234–40. https://doi.org/10.1093/bioinformatics/btz682.

Li, Yunxiang, Zihan Li, Kai Zhang, Ruilong Dan, Steve Jiang, and You Zhang. 2023. “ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge.” arXiv:2303.14070. Preprint, arXiv. https://arxiv.org/abs/2303.14070.

Luo, Renqian, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon, and Tie-Yan Liu. 2022. “BioGPT: Generative Pre-Trained Transformer for Biomedical Text Generation and Mining.” Briefings in Bioinformatics 23 (6): bbac409. https://doi.org/10.1093/bib/bbac409.

Meta AI. 2024. “Introducing Meta Llama 3: The Most Capable Openly Available LLM to Date.” Meta AI Blog. https://ai.meta.com/blog/meta-llama-3/.

OpenAI. 2023. “GPT-4 Technical Report.” arXiv:2303.08774. Preprint, arXiv. https://arxiv.org/abs/2303.08774.

Sanh, Victor, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. “DistilBERT, a Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter.” arXiv:1910.01108. Preprint, arXiv. https://arxiv.org/abs/1910.01108.

Singhal, Karan, Shekoofeh Azizi, Tao Tu, S. Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, et al. 2023a. “Large Language Models Encode Clinical Knowledge.” Nature 620 (7972): 172–80. https://doi.org/10.1038/s41586-023-06291-2.

Singhal, Karan, Tao Tu, Juraj Gottweis, Rory Sayres, Ellery Wulczyn, Le Hou, Kevin Clark, et al. 2023b. “Towards Expert-Level Medical Question Answering with Large Language Models.” arXiv:2305.09617. Preprint, arXiv. https://arxiv.org/abs/2305.09617.

Strubell, Emma, Ananya Ganesh, and Andrew McCallum. 2019. “Energy and Policy Considerations for Deep Learning in NLP.” In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 3645–50. Association for Computational Linguistics. https://doi.org/10.18653/v1/P19-1355.

World Health Organization. 2023. WHO Health Workforce Support and Safeguards List 2023. https://www.who.int/publications/i/item/9789240069787.

Downloads

Published

2026-11-16

How to Cite

Verma, A. (2026). Bridging the Medical Knowledge Gap: 4-bit QLoRA Fine-Tuning of Llama-3-8B for Biomedical Reasoning. Pittsburgh Undergraduate Review, 5(2). https://doi.org/10.5195/pur.2026.166