Significant accuracy improvements are achieved across seven observables, including charge radii, masses, binding energies, separation energies, and decay energies, with the training loss decreasing by over 98% across all tasks.
Abstract
A prior-informed large language model (LLM) driven multi-task learning framework is proposed for the unified and accurate description of multiple nuclear observables. By fine-tuning the pre-trained DeepSeek-R1-1.5B model with Low-Rank Adaptation (LoRA), lightweight adapters are introduced while preserving general pre-trained parameters. Under a causal language modeling paradigm, the model is trained autoregressively on deviations between experimental and theoretical values. Significant accuracy improvements are achieved across seven observables, including charge radii, masses, binding energies, separation energies, and decay energies, with the training loss decreasing by over 98% across all tasks. This demonstrates that the LLM-based framework, through structured prior embedding, offers an efficient and shared approach for multi-task regression in fundamental nuclear properties.
Foundation models often obtain powerful results through very large unlabeled training datasets that dwarf available labeled datasets in size, but high energy physics already provides large samples of high-fidelity labeled simulation. We therefore ask whether self-supervised objectives improve over supervised pretrainin...
Much of the recent progress in machine learning domains such as language models has come from scaling laws that predict performance as a function of training effort. In high-energy physics (HEP) similar behavior has now been observed. To aid further study, we present a systematic procedure to derive robust scaling laws...
The limited transferability of machine-learned interatomic potentials (MLIPs) to unseen chemical compositions constrains their utility in computational materials discovery. We present a systematic investigation into two interdependent design principleslearned atomic representations and cross-element parameterizationt...
M. Taleblou, Franco Pellegrini, Stefano de Gironcoli· Journal of Chemical Informat...· 0 citations
Supervised machine learning in high-energy physics (HEP) requires training on labeled simulations of particle collisions, which are known to be unfaithful to the underlying physics. This leads to significant inaccuracies and biases in the transfer of trained models to real data, limiting the power of deep learning meth...
Zichun Hao, R. Kansal, A. Gandrakota et al.· 0 citations
Reconstructing the mass of a heavy resonance from its decay products with missing energy is one of the central tasks that directly determine the sensitivity in new physics searches at collider experiments. Supervised learning approaches to this problem often struggle to generalize well due to the presence of various sy...
Ho-Fung Tsoi, Alex Yang, Luis Felipe Gutierrez Zagazeta et al.· 0 citations
Hold-out ensembles based on NuCLR (Nuclear Co-Learned Representations), a multi-task model of nuclear data, are developed to study charge radii and electric-quadrupole transition strengths and error bars estimate the expected prediction accuracy across the nuclear chart.
G. Giacalone, S. Trifinopoulos, Mike Williams· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
