Language-Guided Hypotheses Generation for Sparse SMEFT Analyses

Abstract

Global fits of the Standard Model Effective Field Theory are challenged by the large number of operators, while any given database constrains only a small subset. Selecting relevant operator hypotheses therefore requires theoretical insight into operator correlations and the sensitivity of observables. We present llm4smeft, an open source framework that addresses this problem by combining a language model, fine-tuned on the SMEFT literature, with retrieval augmented generation based on quantitative summaries of SMEFiT package global fits. Given a set of observables, the framework proposes candidate relevant operators together with their corresponding Fisher information, while retrieval ensures that model outputs are grounded in existing fit results whenever available. The framework runs in an interactive mode in which accepted hypotheses are stored in a growing knowledge base. We publicly release the llm4smeft package together with the fine-tuned language model, in which the entire framework runs locally, requiring neither internet access nor paid cloud services.

Scaling RIFT 1: Extending RIFT to third-generation gravitational-wave analyses
R. O'Shaughnessy, A. Jan, J. Lange +1
arXiv29 Sep 2026PreprintarXiv licenceFull textInstrumentation & methods Gravitation & general relativityarXiv
P^2-Gaussian: Prior-Driven and Projection-Guided Gaussian Splatting for Sparse-View Cone-Beam CT Reconstruction
Jinqiu Xia, Jianhui Ma, Bin Ouyang +3
arXiv29 Oct 2026PreprintarXiv licenceFull textBiological & medical physicsarXiv
Renormalization-guided cascade upscaling for lattice field generation
Anna Hasenfratz, Ethan T. Neil, Letizia Parato +1
arXiv13 Oct 2026PreprintarXiv licenceFull textHigh-energy & particle physicsarXiv
Text-guided flow matching enables sample-efficient crystal structure generation
Wentao Li
arXiv6 Sep 2026PreprintCC BY-NC-SA 4.0Full textCondensed matterarXiv
Variational Quantum Transformer Architecture for Synthetic Language Generation
Julian Hager, Michael Kölle, Gerhard Stenzel +3
arXiv16 Sep 2026PreprintarXiv licenceFull textQuantum physics & quantum informationarXiv

Cite

BibTeX RIS

BibTeX

@misc{hammad2026languageguided,
  title = {{Language-Guided Hypotheses Generation for Sparse SMEFT Analyses}},
  author = {Ahmed Hammad and Veronica Sanz},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2608.04100},
  eprint = {2608.04100},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.04100},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Language-Guided Hypotheses Generation for Sparse SMEFT Analyses
AU  - Ahmed Hammad
AU  - Veronica Sanz
PY  - 2026
DA  - 2026/09/03
PB  - arXiv
DO  - 10.48550/arxiv.2608.04100
UR  - https://arxiv.org/abs/2608.04100
AB  - Global fits of the Standard Model Effective Field Theory are challenged by the large number of operators, while any given database constrains only a small subset. Selecting relevant operator hypotheses therefore requires theoretical insight into operator correlations and the sensitivity of observables. We present llm4smeft, an open source framework that addresses this problem by combining a language model, fine-tuned on the SMEFT literature, with retrieval augmented generation based on quantitative summaries of SMEFiT package global fits. Given a set of observables, the framework proposes candidate relevant operators together with their corresponding Fisher information, while retrieval ensures that model outputs are grounded in existing fit results whenever available. The framework runs in an interactive mode in which accepted hypotheses are stored in a growing knowledge base. We publicly release the llm4smeft package together with the fine-tuned language model, in which the entire framework runs locally, requiring neither internet access nor paid cloud services.
ER  -

Abstract

Related

Cite