TianHui: A Domain-Specific Large Language Model for Diverse Traditional Chinese Medicine Scenarios
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911227477753856 |
|---|---|
| author | Yin, Ji He, Menglan Zhang, Yujie Zhang, Linshuai Ma, Tingting Tian, Ce Wu, Jie Xu, Lin Jiang, Tao |
| author_facet | Yin, Ji He, Menglan Zhang, Yujie Zhang, Linshuai Ma, Tingting Tian, Ce Wu, Jie Xu, Lin Jiang, Tao |
| contents | Domain-specific LLMs in TCM face limitations in research settings due to constrained adaptability, insufficient evaluation datasets, and limited computational resources. This study presents TianHui, a specialized TCM LLM built through contextual data integration and domain knowledge fusion. We constructed a large-scale TCM corpus (0.97GB unsupervised data + 611,312 QA pairs) and employed a two-stage training strategy with QLoRA, DeepSpeed Stage 2, and Flash Attention 2. Evaluation on 12 benchmarks showed TianHui ranked top-three in all metrics for six datasets (APQ, TCMCD, HFR, HCCA, DHPE, TLAW) and achieved top results in the other six (TCMEE, APR, GCPMI, TCMKQA, TCMRC, ADTG). Optimal configuration was identified as LoRA rank=128, alpha=256, epoch=4, dropout=0.2, max length=2048. TianHui enables systematic preservation and scalable application of TCM knowledge. All resources are open-sourced. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19834 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TianHui: A Domain-Specific Large Language Model for Diverse Traditional Chinese Medicine Scenarios Yin, Ji He, Menglan Zhang, Yujie Zhang, Linshuai Ma, Tingting Tian, Ce Wu, Jie Xu, Lin Jiang, Tao Computation and Language Artificial Intelligence Domain-specific LLMs in TCM face limitations in research settings due to constrained adaptability, insufficient evaluation datasets, and limited computational resources. This study presents TianHui, a specialized TCM LLM built through contextual data integration and domain knowledge fusion. We constructed a large-scale TCM corpus (0.97GB unsupervised data + 611,312 QA pairs) and employed a two-stage training strategy with QLoRA, DeepSpeed Stage 2, and Flash Attention 2. Evaluation on 12 benchmarks showed TianHui ranked top-three in all metrics for six datasets (APQ, TCMCD, HFR, HCCA, DHPE, TLAW) and achieved top results in the other six (TCMEE, APR, GCPMI, TCMKQA, TCMRC, ADTG). Optimal configuration was identified as LoRA rank=128, alpha=256, epoch=4, dropout=0.2, max length=2048. TianHui enables systematic preservation and scalable application of TCM knowledge. All resources are open-sourced. |
| title | TianHui: A Domain-Specific Large Language Model for Diverse Traditional Chinese Medicine Scenarios |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.19834 |