# LLMComp: A Language Modeling Paradigm for Error-Bounded Scientific Data Compression (Technical Report)

arXiv: https://arxiv.org/abs/2510.23632 · HTML: https://mlsanity.com/paper/2510.23632/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 24 Oct 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [Large Language Models for Time Series: A Survey](https://mlsanity.com/paper/2402.01801/) (2024)
- [SZ3: A Modular Framework for Composing Prediction-Based Error-Bounded Lossy Compressors](https://mlsanity.com/paper/2111.02925/) (2021)
- [How Can Large Language Models Understand Spatial-Temporal Data?](https://mlsanity.com/paper/2401.14192/) (2024)
- [Compressing multidimensional weather and climate data into neural networks](https://mlsanity.com/paper/2210.12538/) (2022)
- [CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformer](https://mlsanity.com/paper/2405.03376/) (2024)
- [Exploring Autoencoder-based Error-bounded Compression for Scientific Data](https://mlsanity.com/paper/2105.11730/) (2021)
- [SDRBench: Scientific Data Reduction Benchmark for Lossy Compressors](https://mlsanity.com/paper/2101.03201/) (2021)
- [High-performance Effective Scientific Error-bounded Lossy Compression with Auto-tuned Multi-component Interpolation](https://mlsanity.com/paper/2311.12133/) (2023)
- [Neural Compression of Atmospheric States](https://mlsanity.com/paper/2407.11666/) (2024)

## Abstract (arXiv)

The rapid growth of high-resolution scientific simulations and observation systems is generating massive spatiotemporal datasets, making efficient, error-bounded compression increasingly important. Meanwhile, decoder-only large language models (LLMs) have demonstrated remarkable capabilities in modeling complex sequential data. In this paper, we propose LLMCOMP, a novel lossy compression paradigm that leverages decoder-only large LLMs to model scientific data. LLMCOMP first quantizes 3D fields into discrete tokens, arranges them via Z-order curves to preserve locality, and applies coverage-guided sampling to enhance training efficiency. An autoregressive transformer is then trained with spatial-temporal embeddings to model token transitions. During compression, the model performs top-k prediction, storing only rank indices and fallback corrections to ensure strict error bounds. Experiments on multiple reanalysis datasets show that LLMCOMP consistently outperforms state-of-the-art compressors, achieving up to 30% higher compression ratios under strict error bounds. These results highlight the potential of LLMs as general-purpose compressors for high-fidelity scientific data.