參考文獻
共 33 筆，依關卡分組（每筆放在最先引用它的關卡，其他關卡列在條目下方）。 PubMed 文獻的書目由 NCBI 取得；網頁連結只列網址，不代表內容經過逐句查證。
LV.01 裝備檢查站 （1 筆）
- research.google.com/colaboratory/faq.html
LV.02 PHI 結界 （4 筆）
- www.law.cornell.edu/cfr/text/45/164.514
- law.moj.gov.tw/LawClass/LawAll.aspx?pcode=I0050022
- law.moj.gov.tw/LawClass/LawAll.aspx?pcode=I0050021
- medicine.stanford.edu/news/stories/2025/04/stanford-tech-tools.html
LV.03 AI 家族譜：規則、ML、DL 到 LLM （3 筆）
- Esteva A, Robicquet A, Ramsundar B et al. A guide to deep learning in healthcare. Nat Med. 2019.
- Thirunavukarasu AJ, Ting DSJ, Elangovan K et al. Large language models in medicine. Nat Med. 2023.
- Chen MC, Ruan SJ, Wu JH et al. Classifying American Society of Anesthesiologists Physical Status With a Low-Rank-Adapted Large Language Model: Development and Validation Study. J Med Internet Res. 2026.
LV.04 文字接龍與 Token （2 筆）
- poloclub.github.io/transformer-explainer/
- github.com/rasbt/LLMs-from-scratch
LV.05 注意力與工作記憶 （3 筆）
- jalammar.github.io/illustrated-transformer/
- www.3blue1brown.com/topics/neural-networks
- lmstudio.ai/
LV.06 模型圖鑑與量化 （1 筆）
- Bornet A, Sandralegar A, Yazdani A et al. Impact of LLM Scale and Quantization on Information Extraction from Clinical Text. Stud Health Technol Inform. 2026.
LV.08 本地診間：不訓練也能做的事 （4 筆）
- Mukherjee P, Hou B, Lanfredi RB et al. Feasibility of Using the Privacy-preserving Large Language Model Vicuna for Labeling Radiology Reports. Radiology. 2023.
- Zaghir J, Naguib M, Bjelogrlic M et al. Prompt Engineering Paradigms for Medical Applications: Scoping Review. J Med Internet Res. 2024.
- Woźnicki P, Laqua C, Fiku I et al. Automatic structuring of radiology reports with on-premise open-source large language models. Eur Radiol. 2025.
- Langenbach MC, Foldyna B, Hadzic I et al. Automated anonymization of radiology reports: comparison of publicly available natural language processing and large language models. Eur Radiol. 2025.
LV.09 岔路口：Prompt、RAG、Fine-tune、規則 （1 筆）
- Chen Q, Hu Y, Peng X et al. Benchmarking large language models for biomedical natural language processing applications and recommendations. Nat Commun. 2025.
LV.11 資料煉成所 （1 筆）
- Liu L, Lian L, Hao Y et al. Human level information extraction from clinical reports with finetuned language models. Sci Rep. 2025.
LV.12 秩之神殿：LoRA 與 QLoRA （2 筆）
- Dorémus O, Russon D, Contrand B et al. Harnessing Moderate-Sized Language Models for Reliable Patient Data Deidentification in Emergency Department Records: Algorithm Development, Validation, and Implementation Study. JMIR AI. 2025.
- Helder M, Olsen CM, Pandeya N et al. Automated identification of keratinocyte cancers in pathology reports using large language models. PLOS Digit Health. 2026.
LV.16 分科遠征：結構化抽取、SOAP 與衛教口吻 （3 筆）
- Van Veen D, Van Uden C, Blankemeier L et al. Adapted large language models can outperform medical experts in clinical text summarization. Nat Med. 2024.
- Asgari E, Montaña-Brown N, Dubois M et al. A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation. NPJ Digit Med. 2025.
- Li W, Feng H, Hu C et al. Accurate discharge summary generation using fine tuned large language models with self evaluation. Sci Rep. 2026.
LV.18 反指標沼澤：什麼時候不該用 LLM （2 筆）
- Doo FX, Savani D, Kanhere A et al. Optimal Large Language Model Characteristics to Balance Accuracy and Energy Use for Sustainable Medical Applications. Radiology. 2024.
- Wu YC, Wu YC, Chang YC et al. Advancing medical AI: GPT-4 and GPT-4o surpass GPT-3.5 in Taiwanese medical licensing exams. PLoS One. 2025.
LV.19 結業殿：真實案例與進階路線 （6 筆）
- github.com/mlabonne/llm-course
- Jiang LY, Liu XC, Nejatian NP et al. Health system-scale language models are all-purpose prediction engines. Nature. 2023.
- Lee YQ, Chen CT, Chen CC et al. Unlocking the Secrets Behind Advanced Artificial Intelligence Language Models in Deidentifying Chinese-English Mixed Clinical Text: Development and Validation Study. J Med Internet Res. 2024.
- Richter-Pechanski P, Dieterich C. On-Premise Detection of a Guideline-Driven Oral Anticoagulation Shift in German Doctors' Letters Using Local Large Language Models. Stud Health Technol Inform. 2026.
- Bakr A, Garcia-Agundez A, Atkison T et al. MEDAL: Sequential adapter learning for privacy-preserving multicenter clinical language models. J Biomed Inform. 2026.
- Li M, Chen D, Xiao Q et al. Automated Identification of Nursing Diagnoses and Interventions From Nursing Records Using a Retrieval-Augmented Large Language Model Approach: Quantitative Study. J Med Internet Res. 2026.