Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2305.06488 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929246160551936 |
|---|---|
| author | Lobentanzer, Sebastian Feng, Shaohong Consortium, The BioChatter Maier, Andreas Wang, Cankun Baumbach, Jan Krehl, Nils Ma, Qin Saez-Rodriguez, Julio |
| author_facet | Lobentanzer, Sebastian Feng, Shaohong Consortium, The BioChatter Maier, Andreas Wang, Cankun Baumbach, Jan Krehl, Nils Ma, Qin Saez-Rodriguez, Julio |
| contents | Current-generation Large Language Models (LLMs) have stirred enormous interest in recent months, yielding great potential for accessibility and automation, while simultaneously posing significant challenges and risk of misuse. To facilitate interfacing with LLMs in the biomedical space, while at the same time safeguarding their functionalities through sensible constraints, we propose a dedicated, open-source framework: BioChatter. Based on open-source software packages, we synergise the many functionalities that are currently developing around LLMs, such as knowledge integration / retrieval-augmented generation, model chaining, and benchmarking, resulting in an easy-to-use and inclusive framework for application in many use cases of biomedicine. We focus on robust and user-friendly implementation, including ways to deploy privacy-preserving local open-source LLMs. We demonstrate use cases via two multi-purpose web apps (https://chat.biocypher.org), and provide documentation, support, and an open community. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_06488 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Platform for the Biomedical Application of Large Language Models Lobentanzer, Sebastian Feng, Shaohong Consortium, The BioChatter Maier, Andreas Wang, Cankun Baumbach, Jan Krehl, Nils Ma, Qin Saez-Rodriguez, Julio Quantitative Methods Current-generation Large Language Models (LLMs) have stirred enormous interest in recent months, yielding great potential for accessibility and automation, while simultaneously posing significant challenges and risk of misuse. To facilitate interfacing with LLMs in the biomedical space, while at the same time safeguarding their functionalities through sensible constraints, we propose a dedicated, open-source framework: BioChatter. Based on open-source software packages, we synergise the many functionalities that are currently developing around LLMs, such as knowledge integration / retrieval-augmented generation, model chaining, and benchmarking, resulting in an easy-to-use and inclusive framework for application in many use cases of biomedicine. We focus on robust and user-friendly implementation, including ways to deploy privacy-preserving local open-source LLMs. We demonstrate use cases via two multi-purpose web apps (https://chat.biocypher.org), and provide documentation, support, and an open community. |
| title | A Platform for the Biomedical Application of Large Language Models |
| topic | Quantitative Methods |
| url | https://arxiv.org/abs/2305.06488 |