IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yiming, Chang, Zheng, Cai, Wentao, Ren, MengXing, Yuan, Kang, Sun, Yining, Ding, Zenghui
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912178217418752
author Zhang, Yiming
Chang, Zheng
Cai, Wentao
Ren, MengXing
Yuan, Kang
Sun, Yining
Ding, Zenghui
author_facet Zhang, Yiming
Chang, Zheng
Cai, Wentao
Ren, MengXing
Yuan, Kang
Sun, Yining
Ding, Zenghui
contents Recent researches of large language models(LLM), which is pre-trained on massive general-purpose corpora, have achieved breakthroughs in responding human queries. However, these methods face challenges including limited data insufficiency to support extensive pre-training and can not align responses with users' instructions. To address these issues, we introduce a medical instruction dataset, CMedINS, containing six medical instructions derived from actual medical tasks, which effectively fine-tunes LLM in conjunction with other data. Subsequently, We launch our medical model, IIMedGPT, employing an efficient preference alignment method, Direct preference Optimization(DPO). The results show that our final model outperforms existing medical models in medical dialogue.Datsets, Code and model checkpoints will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2501_02869
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment
Zhang, Yiming
Chang, Zheng
Cai, Wentao
Ren, MengXing
Yuan, Kang
Sun, Yining
Ding, Zenghui
Computation and Language
Artificial Intelligence
Recent researches of large language models(LLM), which is pre-trained on massive general-purpose corpora, have achieved breakthroughs in responding human queries. However, these methods face challenges including limited data insufficiency to support extensive pre-training and can not align responses with users' instructions. To address these issues, we introduce a medical instruction dataset, CMedINS, containing six medical instructions derived from actual medical tasks, which effectively fine-tunes LLM in conjunction with other data. Subsequently, We launch our medical model, IIMedGPT, employing an efficient preference alignment method, Direct preference Optimization(DPO). The results show that our final model outperforms existing medical models in medical dialogue.Datsets, Code and model checkpoints will be released upon acceptance.
title IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2501.02869