A CMS AI to Improve Paper Publishing

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Authors: Álvarez-Cascos, Annunziata, Rehm, Florian
Format: Recurso digital
Published: Zenodo 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866902245533024256
author Álvarez-Cascos, Annunziata
Rehm, Florian
author_facet Álvarez-Cascos, Annunziata
Rehm, Florian
contents <p>This project explores the potential of AI-powered automation in the peer review process for CMS experiment publications at CERN, using the LLaMA 3.1 language model. The research initially employed a fine-tuning approach through Parameter-Efficient Fine-Tuning (PEFT), which, while effective in automating certain aspects such as ensuring consistency with formatting and style guidelines, required significant resources and time. To address these limitations, a prompt engineering approach was later adopted, significantly reducing the time required while improving the accuracy and consistency of reviews. By embedding a summary of CMS internal publication guidelines directly within the prompts, the model was able to perform without additional task-specific training. Both approaches demonstrated the potential for AI to streamline the peer review process, with the prompt engineering method showing particular promise in efficiency. The findings lay a strong foundation for future improvements, including further customization of training processes, dataset expansion, and the development of a graphical user interface (GUI), while also contributing valuable insights into the current capabilities and limitations of AI models in specialized domains.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_13856034
institution Zenodo
language
publishDate 2024
publisher Zenodo
record_format zenodo
spellingShingle A CMS AI to Improve Paper Publishing
Álvarez-Cascos, Annunziata
Rehm, Florian
CERN openlab summer student project
<p>This project explores the potential of AI-powered automation in the peer review process for CMS experiment publications at CERN, using the LLaMA 3.1 language model. The research initially employed a fine-tuning approach through Parameter-Efficient Fine-Tuning (PEFT), which, while effective in automating certain aspects such as ensuring consistency with formatting and style guidelines, required significant resources and time. To address these limitations, a prompt engineering approach was later adopted, significantly reducing the time required while improving the accuracy and consistency of reviews. By embedding a summary of CMS internal publication guidelines directly within the prompts, the model was able to perform without additional task-specific training. Both approaches demonstrated the potential for AI to streamline the peer review process, with the prompt engineering method showing particular promise in efficiency. The findings lay a strong foundation for future improvements, including further customization of training processes, dataset expansion, and the development of a graphical user interface (GUI), while also contributing valuable insights into the current capabilities and limitations of AI models in specialized domains.</p>
title A CMS AI to Improve Paper Publishing
topic CERN openlab summer student project
url https://doi.org/10.5281/zenodo.13856034