Fetching the paper…

Reading the bibliography…

2025

Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs

Le, Chenqian, Gong, Ziheng, Wang, Chihang et al.

Original
PDF
Post on X

Understand

Large language models (LLMs) have shown great potential in medical question answering (MedQA), yet adapting them to biomedical reasoning remains challenging due to domain-specific complexity and limited supervision.

In this work, we study how prompt design and lightweight fine-tuning affect the performance of open-source LLMs on PubMedQA, a benchmark for multiple-choice biomedical questions.
We focus on two widely used prompting strategies - standard instruction prompts and Chain-of-Thought (CoT) prompts - and apply QLoRA for parameter-efficient instruction tuning.
Across multiple model families and sizes, our experiments show that CoT prompting alone can improve reasoning in zero-shot settings, while instruction tuning significantly boosts accuracy.

Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs · Around

Built on

I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” arXiv preprint arXiv:1711.05101 , 2017
Original
2017
Earlier work this paper cites.
Q. Jin et al. , “Pubmedqa: A dataset for biomedical research question answering,” arXiv:1909.06146 , 2019
Original
2019
Earlier work this paper cites.
J. Lee et al. , “Biobert: a pre-trained biomedical language representation model for biomedical text mining,” Bioinformatics , 2020
2020
Earlier work this paper cites.
T. Zhang, B. Zhang, F. Zhao, and S. Zhang, “Covid-19 localization and recognition on chest radiographs based on yolov5 and efficientnet,” in 2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) . IEEE, 2022, pp. 1827–1830
2022
Earlier work this paper cites.
J. Wei et al. , “Chain-of-thought prompting elicits reasoning in large language models,” Advances in neural information processing systems , 2022
2022
Earlier work this paper cites.
Y. Ji, Y. Gao, R. Bao, Q. Li, D. Liu, Y. Sun, and Y. Ye, “Prediction of covid-19 patients’ emergency room revisit using multi-source transfer learning,” in 2023 IEEE 11th International Conference on Healthcare Informatics (ICHI) . IEEE, 2023, pp. 138–144
2023
Earlier work this paper cites.
Z. Luo, Y. Ji et al. , “Towards accurate and clinically meaningful summarization of electronic health record notes: A guided approach,” in 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI) . IEEE, 2023, pp. 1–5
2023
Earlier work this paper cites.
J. Achiam et al. , “Gpt-4 technical report,” arXiv preprint arXiv:2303.08774 , 2023
Original
2023
Earlier work this paper cites.
T. Dettmers et al. , “Qlora: Efficient finetuning of quantized llms,” arXiv preprint arXiv:2305.14314 , 2023
Original
2023
Earlier work this paper cites.
S. Zhang et al. , “Instruction tuning for large language models: A survey,” arXiv:2308.10792 , 2023
Original
2023
Earlier work this paper cites.

Similar

Y. Ji, Z. Yu, and Y. Wang, “Assertion detection in clinical natural language processing using large language models,” in 2024 IEEE 12th International Conference on Healthcare Informatics (ICHI) , 2024, pp. 242–247
2024
Cited alongside, same era.
Z. Yang, Y. Jin, and X. Xu, “Hades: Hardware accelerated decoding for efficient speculation in large language models,” arXiv preprint arXiv:2412.19925 , 2024
Original
2024
Cited alongside, same era.
M. Sui, C. Zhang, L. Zhou, S. Liao, and C. Wei, “An ensemble approach to stock price prediction using deep learning and time series models,” in 2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems (ICPICS) . IEEE, 2024, pp. 793–797
2024
Cited alongside, same era.
S. Liu, Y. Lu, S. Chen, X. Hu, J. Zhao, Y. Lu, and Y. Zhao, “Drugagent: Automating ai-aided drug discovery programming through llm multi-agent collaboration,” arXiv preprint arXiv:2411.15692 , 2024
Original
2024
Cited alongside, same era.

Then

T. Ding, D. Xiang, T. Sun, Y. Qi, and Z. Zhao, “Ai-driven prognostics for state of health prediction in li-ion batteries: A comprehensive analysis with validation,” arXiv preprint arXiv:2504.05728 , 2025
Original
2025
Closest in time.
Z. Yang, Y. Jin, Y. Zhang, J. Liu, and X. Xu, “Research on large language model cross-cloud privacy protection and collaborative training based on federated learning,” arXiv preprint arXiv:2503.12226 , 2025
Original
2025
Closest in time.
Y. Jin, Z. Yang, X. Xu, Y. Zhang, and S. Ji, “Adaptive fault tolerance mechanisms of large language models in cloud computing environments,” arXiv preprint arXiv:2503.12228 , 2025
Original
2025
Closest in time.
L. Zhang, R. Liang et al. , “Avocado price prediction using a hybrid deep learning model: Tcn-mlp-attention architecture,” arXiv preprint arXiv:2505.09907 , 2025
Original
2025
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Y. Ji, Z. Li, R. Meng, S. Sivarajkumar et al. , “RAG-RLRC-LaySum at BioLaySumm: Integrating retrieval-augmented generation and readability control for layman summarization of biomedical texts,” in Proceedings of the 23rd Workshop on Biomedical Natural Language Processing , 2024, pp. 810–817

2024

Cited alongside, same era.

E. Bolton et al. , “Biomedlm: A 2.7 b parameter language model trained on biomedical text,” arXiv , 2024

2024

Cited alongside, same era.

A. Grattafiori et al. , “The llama 3 herd of models,” arXiv preprint arXiv:2407.21783 , 2024

2024

Cited alongside, same era.

A. Yang et al. , “Qwen2. 5 technical report,” arXiv preprint arXiv:2412.15115 , 2024

2024

Cited alongside, same era.

B. Xu, Y. Lu, C. Li, L. Yue, X. Wang, N. Hao, T. Fu, and J. Chen, “Smiles-mamba: Chemical mamba foundation models for drug admet prediction,” arXiv preprint arXiv:2408.05696 , 2024

2024

Cited alongside, same era.

L. Yue, S. Xing, Y. Lu, and T. Fu, “Biomamba: A pre-trained biomedical language representation model leveraging mamba,” arXiv preprint arXiv:2408.02600 , 2024

2024

Cited alongside, same era.

H. Luo and C. Ji, “Cross-cloud data privacy protection: Optimizing collaborative mechanisms of ai systems by integrating federated learning and llms,” arXiv preprint arXiv:2505.13292 , 2025

2025

Closest in time.

Z. Yang, Y. Jin, J. Liu, X. Xu, Y. Zhang, and S. Ji, “Research on cloud platform network traffic monitoring and anomaly detection system based on large language models,” arXiv preprint arXiv:2504.17807 , 2025

2025

Closest in time.

C. Ji and H. Luo, “Cloud-based ai systems: Leveraging large language models for intelligent fault detection and autonomous self-healing,” arXiv preprint arXiv:2505.11743 , 2025

2025

Closest in time.

T. K. Ding, D. Xiang, Y. Qi, Z. Yang, Z. Zhao, T. Sun, P. Feng, and H. Wang, “Nerf-based defect detection,” in International Conference on Remote Sensing, Mapping, and Image Processing (RSMIP 2025) , vol. 13650. SPIE, 2025, pp. 368–373

2025

Closest in time.

T. Ding, D. Xiang, P. Rivas, and L. Dong, “Neural pruning for 3d scene reconstruction: Efficient nerf acceleration,” arXiv preprint arXiv:2504.00950 , 2025

2025

Closest in time.

K. Singhal et al. , “Toward expert-level medical question answering with large language models,” Nature Medicine , 2025

2025

Closest in time.