Fine-grained Alignment of Large Language Models for General Medication Recommendation without Overprescription
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911087685795840 |
|---|---|
| author | Zhao, Zihao Fan, Chenxiao Liu, Junlong Wang, Zheng He, Xiangnan Gao, Chongming Li, Juan Feng, Fuli |
| author_facet | Zhao, Zihao Fan, Chenxiao Liu, Junlong Wang, Zheng He, Xiangnan Gao, Chongming Li, Juan Feng, Fuli |
| contents | Large language models (LLMs) holds significant promise in achieving general medication recommendation systems owing to their comprehensive interpretation of clinical notes and flexibility to medication encoding. We evaluated both general-purpose and medical-specific LLMs for medication recommendations, showing their unsatisfactory precision and severe overprescription. To address this, we introduce Language-Assisted Medication Recommendation, which tailors LLMs for medication recommendation in a medication-aware manner, improving the usage of clinical notes. Fine-tuning LLMs with this framework can outperform existing methods by more than 10% in internal validation and generalize across temporal and external validations. Furthermore, the model maintains high accuracy when encountering out-of-distribution medication. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03687 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-grained Alignment of Large Language Models for General Medication Recommendation without Overprescription Zhao, Zihao Fan, Chenxiao Liu, Junlong Wang, Zheng He, Xiangnan Gao, Chongming Li, Juan Feng, Fuli Information Retrieval Large language models (LLMs) holds significant promise in achieving general medication recommendation systems owing to their comprehensive interpretation of clinical notes and flexibility to medication encoding. We evaluated both general-purpose and medical-specific LLMs for medication recommendations, showing their unsatisfactory precision and severe overprescription. To address this, we introduce Language-Assisted Medication Recommendation, which tailors LLMs for medication recommendation in a medication-aware manner, improving the usage of clinical notes. Fine-tuning LLMs with this framework can outperform existing methods by more than 10% in internal validation and generalize across temporal and external validations. Furthermore, the model maintains high accuracy when encountering out-of-distribution medication. |
| title | Fine-grained Alignment of Large Language Models for General Medication Recommendation without Overprescription |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2503.03687 |