It is argued that replacing autoregressive LLMs with DLMs within the same compression framework could overcome the throughput bottleneck caused by their one-symbol-per-step limitation, and the newly proposed DLM-based framework advances the state of the art in lossless text compression.
Abstract
We study the problem of lossless text compression, motivated by the rapid growth in the collection and storage of digital textual data - including plain text, source code, and structured formats such as XML - and by recent advances in neural language model-based compression. In particular, recent LLM-based approaches, whether built on symbol-ranking pipelines or paired with a statistical compressor, have demonstrated compression ratios significantly superior to general-purpose compressors such as zstd, gzip, or bzip on text and code. However, these neural approaches suffer from severe throughput limitations, making them not yet practically usable. For the first time in the context of lossless neural text compression, we introduce Diffusion Language Models (DLMs) as an alternative inference paradigm to autoregressive LLM-based approaches. We argue that replacing autoregressive LLMs with DLMs within the same compression framework could overcome the throughput bottleneck caused by their one-symbol-per-step limitation. However, achieving these improvements requires addressing algorithmic challenges introduced by applying DLMs to lossless compression, where the architecture allows the number and positions of symbols encoded at each forward pass to be decided independently. We design efficient and effective strategies to solve these challenges and evaluate them experimentally against LLM-based and general-purpose compressors on enwik8, a well-established textual benchmark. Our results show that the newly proposed DLM-based framework advances the state of the art in lossless text compression. Moreover, as DLMs are still a relatively young paradigm, recent advances toward increasingly capable and efficient models suggest substantial room for further improvements.
We study the problem of lossless compression of source code, motivated by the storage demands of large-scale software archives, such as Software Heritage (https://www.softwareheritage.org/). General-purpose compressors (e.g., zstd, bzip2) offer a good trade-off between compression ratio and speed, but fail to exploit all special regularities inherent in source code. Recent approaches leverage Large Language Models (LLMs) within Shannon's symbol-ranking framework, relying on a scheme in which the predicted rank can grow arbitrarily. While effective at reducing space, this setting incurs significant throughput degradation, and leaves open the question whether it is necessary to explicitly encode all ranks. In this work, we introduce LLM-based compressors deploying two novel symbol-ranking variants that bound predictions to the top-$T$ ranks ($T=1$ or $63$), with out-of-threshold symbols stored as exceptions and compressed jointly with the rank stream via general-purpose compressors. We conduct the first large-scale evaluation of LLM-based source code compression across 30 LLMs, including general-domain, code-specialized, and quantized models. Our $T$-bounded approach outperforms prior LLM-based compressors both in compression ratio (up to 37% relative improvement) and compression throughput (40% faster). Compared to general-purpose compressors (e.g., zstd, bzip2), we obtain up to 82% relative compression gain but at a lower speed, thus offering a new trade-off point in the compression-speed spectrum. We also show that these gains are stronger on source code than on natural language, suggesting an interesting indication, namely that source code exposes regularities captured by LLMs but missed by general-purpose exact-match-based compressors. We conclude by commenting on open problems that offer theoretical and practical avenues of research.
Angelo Nardone, P. Ferragina· arXiv.org· 1 citation
Soft context compression condenses a context into a few memory tokens that a frozen LLM consumes in place of the raw text, but existing compressors fix the compression ratio at training and inference: each deployed ratio requires a separately trained model, and the chosen ratio is applied uniformly to all inputs, whose actual needs vary drastically. We propose FlexComp, a method-agnostic framework that decouples the ratio from both training and deployment: Matryoshka-style training samples the memory budget $K$ per instance, turning one model into an any-ratio compressor, and the budget is then chosen per input by: (1) confidence-based cascade routing or (2) a lightweight learned $K$ predictor. Across ICAE, 500xCompressor, and SAC on MRQA, a single FlexComp model matches separately trained fixed-ratio specialists with minimal degradation. Cascade routing preserves over 98% of the mildest ratio's accuracy at up to 266x average compression; the $K$ predictor, in a single compression-decoding pass, reaches 158-236x within 0.7 F1 of the mildest ratio. At serving-scale batch sizes, the $K$ predictor cuts context KV cache by 50% and improves decoding throughput by 47%.
Kai-Yan Zhao, Zhong-Tao Miao, Akiko Aizawa et al.· 0 citations
Retrieval-Augmented Generation (RAG) enhances language models with external knowledge, but the lengthy retrieved context inflates the input and degrades inference efficiency. Soft context compression encodes each document into a substantially shorter embedding sequence. However, most existing approaches are trained by distilling outputs from uncompressed RAG systems, inherently limiting their performance relative to the original model. To address this limitation, we propose DEX-Comp, a two-stage training recipe: Pure Distillation warm-starts the compression model on the uncompressed RAG's correct responses only, and Hard Exploration then runs reinforcement learning solely on queries the uncompressed RAG fails, forcing the model to explore computation patterns better suited to compressed representations. On five open-domain QA benchmarks at retrieval depths from top-5 to top-30, DEX-Comp compresses retrieved contexts by $16\times$ and accelerates inference by $4\times$--$24\times$, while achieving performance comparable to or exceeding the uncompressed RAG baseline across retrieval depths. Ablations and evaluations across diverse datasets and backbones further confirm the contribution of each stage and the generalization of our approach.
HCC directly realizes the hierarchical-compression direction identified as future work by recent segmented-decoding methods, and is validated with controlled and real-text information-retention studies and with direct latency and memory measurements.
Maya Srinivasan, Lucas Bernal· International journal of inf...· 0 citations
Any lossless compression algorithm (like gzip) may be converted into a machine learning method, via either Normalized Compression Distance or the Minimum Description Length principle. Any auto-regressive model may be converted into a lossless compression method via entropy coding. This seemingly circular dependence has unrealized potential in modern artificial intelligence and machine learning, and we survey and formalize the various strategies that have been used to leverage compression for machine learning. We introduce and empirically validate a design framework for compression-based ML, finding compression-based methods competitive with conventional baselines and decisively stronger on malware. We find that varying these design choices yields accuracy gains of up to 0.62.
John Hurwitz, Edward Raff, Charles Nicholas· 0 citations
Cortado is compared with state-of-the-art approaches and it is found that it is the only progressive compressor that guarantees the evaluated error bounds on all tested inputs while achieving the highest throughputs, comparable reconstruction quality, and on-par compression ratios.
B. Burtchell, Martin Burtscher· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
