Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.04388 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908383293997056 |
|---|---|
| author | Garcia-Gasulla, Dario Bayarri-Planas, Jordi Gururajan, Ashwin Kumar Lopez-Cuena, Enrique Tormos, Adrian Hinjos, Daniel Bernabeu-Perez, Pablo Arias-Duart, Anna Martin-Torres, Pablo Agustin Gonzalez-Mallo, Marta Alvarez-Napagao, Sergio Ayguadé-Parra, Eduard Cortés, Ulises |
| author_facet | Garcia-Gasulla, Dario Bayarri-Planas, Jordi Gururajan, Ashwin Kumar Lopez-Cuena, Enrique Tormos, Adrian Hinjos, Daniel Bernabeu-Perez, Pablo Arias-Duart, Anna Martin-Torres, Pablo Agustin Gonzalez-Mallo, Marta Alvarez-Napagao, Sergio Ayguadé-Parra, Eduard Cortés, Ulises |
| contents | Purpose: With advancements in Large Language Models (LLMs) for healthcare, the need arises for competitive open-source models to protect the public interest. This work contributes to the field of open medical LLMs by optimizing key stages of data preprocessing and training, while showing how to improve model safety (through DPO) and efficacy (through RAG). The evaluation methodology used, which includes four different types of tests, defines a new standard for the field. The resultant models, shown to be competitive with the best private alternatives, are released with a permisive license.
Methods: Building on top of strong base models like Llama 3.1 and Qwen 2.5, Aloe Beta uses a custom dataset to enhance public data with synthetic Chain of Thought examples. The models undergo alignment with Direct Preference Optimization, emphasizing ethical and policy-aligned performance in the presence of jailbreaking attacks. Evaluation includes close-ended, open-ended, safety and human assessments, to maximize the reliability of results.
Results: Recommendations are made across the entire pipeline, backed by the solid performance of the Aloe Family. These models deliver competitive performance across healthcare benchmarks and medical fields, and are often preferred by healthcare professionals. On bias and toxicity, the Aloe Beta models significantly improve safety, showing resilience to unseen jailbreaking attacks. For a responsible release, a detailed risk assessment specific to healthcare is attached to the Aloe Family models.
Conclusion: The Aloe Beta models, and the recipe that leads to them, are a significant contribution to the open-source medical LLM field, offering top-of-the-line performance while maintaining high ethical requirements. This work sets a new standard for developing and reporting aligned LLMs in healthcare. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04388 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Aloe Family Recipe for Open and Specialized Healthcare LLMs Garcia-Gasulla, Dario Bayarri-Planas, Jordi Gururajan, Ashwin Kumar Lopez-Cuena, Enrique Tormos, Adrian Hinjos, Daniel Bernabeu-Perez, Pablo Arias-Duart, Anna Martin-Torres, Pablo Agustin Gonzalez-Mallo, Marta Alvarez-Napagao, Sergio Ayguadé-Parra, Eduard Cortés, Ulises Computation and Language Artificial Intelligence Purpose: With advancements in Large Language Models (LLMs) for healthcare, the need arises for competitive open-source models to protect the public interest. This work contributes to the field of open medical LLMs by optimizing key stages of data preprocessing and training, while showing how to improve model safety (through DPO) and efficacy (through RAG). The evaluation methodology used, which includes four different types of tests, defines a new standard for the field. The resultant models, shown to be competitive with the best private alternatives, are released with a permisive license. Methods: Building on top of strong base models like Llama 3.1 and Qwen 2.5, Aloe Beta uses a custom dataset to enhance public data with synthetic Chain of Thought examples. The models undergo alignment with Direct Preference Optimization, emphasizing ethical and policy-aligned performance in the presence of jailbreaking attacks. Evaluation includes close-ended, open-ended, safety and human assessments, to maximize the reliability of results. Results: Recommendations are made across the entire pipeline, backed by the solid performance of the Aloe Family. These models deliver competitive performance across healthcare benchmarks and medical fields, and are often preferred by healthcare professionals. On bias and toxicity, the Aloe Beta models significantly improve safety, showing resilience to unseen jailbreaking attacks. For a responsible release, a detailed risk assessment specific to healthcare is attached to the Aloe Family models. Conclusion: The Aloe Beta models, and the recipe that leads to them, are a significant contribution to the open-source medical LLM field, offering top-of-the-line performance while maintaining high ethical requirements. This work sets a new standard for developing and reporting aligned LLMs in healthcare. |
| title | The Aloe Family Recipe for Open and Specialized Healthcare LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2505.04388 |