Guardado en:
Detalles Bibliográficos
Autores principales: Richmond, Paul, Agarwal, Prarit, Chowdhury, Borun, Niarchos, Vasilis, Papageorgakis, Constantinos
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2508.03716
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917299448971264
author Richmond, Paul
Agarwal, Prarit
Chowdhury, Borun
Niarchos, Vasilis
Papageorgakis, Constantinos
author_facet Richmond, Paul
Agarwal, Prarit
Chowdhury, Borun
Niarchos, Vasilis
Papageorgakis, Constantinos
contents We present specialized Large Language Models for theoretical High-Energy Physics, obtained as 20 fine-tuned variants of the 8-billion parameter Llama-3.1 model. Each variant was trained on arXiv abstracts (through August 2024) from different combinations of hep-th, hep-ph and gr-qc. For a comparative study, we also trained models on datasets that contained abstracts from disparate fields such as the q-bio and cs categories. All models were fine-tuned using two distinct Low-Rank Adaptation fine-tuning approaches and varying dataset sizes, and outperformed the base model on hep-th abstract completion tasks. We compare performance against leading commercial LLMs (ChatGPT, Claude, Gemini, DeepSeek) and derive insights for further developing specialized language models for High-Energy Theoretical Physics.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03716
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FeynTune: Large Language Models for High-Energy Theory
Richmond, Paul
Agarwal, Prarit
Chowdhury, Borun
Niarchos, Vasilis
Papageorgakis, Constantinos
Computation and Language
Machine Learning
High Energy Physics - Theory
We present specialized Large Language Models for theoretical High-Energy Physics, obtained as 20 fine-tuned variants of the 8-billion parameter Llama-3.1 model. Each variant was trained on arXiv abstracts (through August 2024) from different combinations of hep-th, hep-ph and gr-qc. For a comparative study, we also trained models on datasets that contained abstracts from disparate fields such as the q-bio and cs categories. All models were fine-tuned using two distinct Low-Rank Adaptation fine-tuning approaches and varying dataset sizes, and outperformed the base model on hep-th abstract completion tasks. We compare performance against leading commercial LLMs (ChatGPT, Claude, Gemini, DeepSeek) and derive insights for further developing specialized language models for High-Energy Theoretical Physics.
title FeynTune: Large Language Models for High-Energy Theory
topic Computation and Language
Machine Learning
High Energy Physics - Theory
url https://arxiv.org/abs/2508.03716