# TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction

arXiv: https://arxiv.org/abs/2407.10510 · HTML: https://mlsanity.com/paper/2407.10510/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 15 Jul 2024.

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [HuatuoGPT, towards Taming Language Model to Be a Doctor](https://mlsanity.com/paper/2305.15075/) (2023)
- [HuaTuo: Tuning LLaMA Model with Chinese Medical Knowledge](https://mlsanity.com/paper/2304.06975/) (2023)
- [Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue](https://mlsanity.com/paper/2308.03549/) (2023)
- [Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese](https://mlsanity.com/paper/2110.06696/) (2021)
- [Syndrome-aware Herb Recommendation with Multi-Graph Convolution Network](https://mlsanity.com/paper/2002.08575/) (2020)
- [Sequential Condition Evolved Interaction Knowledge Graph for Traditional Chinese Medicine Recommendation](https://mlsanity.com/paper/2305.17866/) (2023)
- [RoKEPG: RoBERTa and Knowledge Enhancement for Prescription Generation of Traditional Chinese Medicine](https://mlsanity.com/paper/2311.17307/) (2023)

## Built on by (most cited first, 4 of 4)

- [TCM-Eval: An Expert-Level Dynamic and Extensible Benchmark for Traditional Chinese Medicine](https://mlsanity.com/paper/2511.07148/) (2025)
- [ZhiFangDanTai: Fine-tuning Graph-based Retrieval-Augmented Generation Model for Traditional Chinese Medicine Formula](https://mlsanity.com/paper/2509.05867/) (2025)
- [MedGo: A Chinese Medical Large Language Model](https://mlsanity.com/paper/2410.20428/) (2024)
- [MMIR-TCM: Memory-Integrated Multimodal Inference and Retrieval for TCM Clinical Decision Support](https://mlsanity.com/paper/2607.01814/) (2026)

## Abstract (arXiv)

Traditional Chinese medicine (TCM) has relied on specific combinations of herbs in prescriptions to treat various symptoms and signs for thousands of years. Predicting TCM prescriptions poses a fascinating technical challenge with significant practical implications. However, this task faces limitations due to the scarcity of high-quality clinical datasets and the complex relationship between symptoms and herbs. To address these issues, we introduce textitDigestDS, a novel dataset comprising practical medical records from experienced experts in digestive system diseases. We also propose a method, TCM-FTP (TCM Fine-Tuning Pre-trained), to leverage pre-trained large language models (LLMs) via supervised fine-tuning on textitDigestDS. Additionally, we enhance computational efficiency using a low-rank adaptation technique. Moreover, TCM-FTP incorporates data augmentation by permuting herbs within prescriptions, exploiting their order-agnostic nature. Impressively, TCM-FTP achieves an F1-score of 0.8031, significantly outperforming previous methods. Furthermore, it demonstrates remarkable accuracy in dosage prediction, achieving a normalized mean square error of 0.0604. In contrast, LLMs without fine-tuning exhibit poor performance. Although LLMs have demonstrated wide-ranging capabilities, our work underscores the necessity of fine-tuning for TCM prescription prediction and presents an effective way to accomplish this.