Prarit Agarwal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Prarit Agarwal has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Borun Chowdhury
Meta, 10 Brock Street, Regents Place, London NW1 3FG, United Kingdom
1 shared publication - Constantinos Papageorgakis
Queen Mary University of London
1 shared publication - Paul Richmond
Centre for Theoretical Physics, Department of Physics and Astronomy, Queen Mary University of London, London E1 4NS, United Kingdom
1 shared publication - Vasilis Niarchos
ITCP & CCTP, Department of Physics, University of Crete, 71003 Heraklion, Greece
1 shared publication
Latest Publications
- Open Access
- 27 February 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (2) , 025012
FeynTune: large language models for high-energy theory
We present specialized large language models (LLMs) 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.
- 27 February 2026
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 7 (2) , 025012
Open AccessFeynTune: large language models for high-energy theory
We present specialized large language models (LLMs) 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.