# From Human Labels to Literature: Semi-Supervised Learning of NMR Chemical Shifts at Scale

arXiv: https://arxiv.org/abs/2601.18524 · HTML: https://mlsanity.com/paper/2601.18524/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 41 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Review and Prospect: Deep Learning in Nuclear Magnetic Resonance Spectroscopy](https://mlsanity.com/paper/2001.04813/) (2020)
- [MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild](https://mlsanity.com/paper/2411.11098/) (2024)
- [NMR-Solver: Automated Structure Elucidation via Large-Scale Spectral Matching and Physics-Guided Fragment Optimization](https://mlsanity.com/paper/2509.00640/) (2025)
- [TransPeakNet: Solvent-Aware 2D NMR Prediction via Multi-Task Pre-Training and Unsupervised Learning](https://mlsanity.com/paper/2403.11353/) (2024)

## Built on by (most cited first, 1 of 1)

- [SpecXMaster Technical Report](https://mlsanity.com/paper/2603.23101/) (2026)

## Abstract (arXiv)

Accurate prediction of nuclear magnetic resonance (NMR) chemical shifts is fundamental to spectral analysis and molecular structure elucidation, yet existing machine learning methods rely on limited, labor-intensive atom-assigned datasets. We propose a semi-supervised framework that learns NMR chemical shifts from millions of literature-extracted spectra without explicit atom-level assignments, integrating a small amount of labeled data with large-scale unassigned spectra. We formulate chemical shift prediction from literature spectra as a permutation-invariant set supervision problem, and show that under commonly satisfied conditions on the loss function, optimal bipartite matching reduces to a sorting-based loss, enabling stable large-scale semi-supervised training beyond traditional curated datasets. Our models achieve substantially improved accuracy and robustness over state-of-the-art methods and exhibit stronger generalization on significantly larger and more diverse molecular datasets. Moreover, by incorporating solvent information at scale, our approach captures systematic solvent effects across common NMR solvents for the first time. Overall, our results demonstrate that large-scale unlabeled spectra mined from the literature can serve as a practical and effective data source for training NMR shift models, suggesting a broader role of literature-derived, weakly structured data in data-centric AI for science.