Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio

• URL: http://arxiv.org/abs/2603.25926v1
• Date: Thu, 26 Mar 2026 21:36:55 GMT
• Title: Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio
• Abstract summary: We introduce Semi-Dynamic Context Compression framework.<n>Our approach features a Discrete Ratio Selector, which predicts a compression target based on intrinsic information density.<n>Our framework consistently outperforms static baselines.
• Score: 19.375601589555327
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing frameworks apply uniform compression ratios, failing to account for the extreme variance in natural language information density. While adopting a density-aware dynamic compression ratio seems intuitive, empirical investigations reveal that models struggle intrinsically with operations parameterized by input dependent, continuous structural hyperparameters. To resolve this pitfall, we introduce Semi-Dynamic Context Compression framework. Our approach features a Discrete Ratio Selector, which predicts a compression target based on intrinsic information density and quantizes it to a predefined set of discrete compression ratios. It is efficiently jointly trained with the compressor on synthetic data, with the summary lengths as a proxy to create labels for compression ratio prediction. Extensive evaluations confirm that our density-aware framework, utilizing mean pooling as the backbone, consistently outperforms static baselines, establishing a robust Pareto frontier for context compression techniques. Our code, data and model weights are available at https://github.com/yuyijiong/semi-dynamic-context-compress

Related papers

• Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor [18.235525350999335]
  This work reveals that a thinking model itself can naturally compress long contexts by organizing task-relevant information.<n>We thus derive Thinking as Compression (TaC), a new compression paradigm that treats thinking itself as compressed context.
  arXiv  Detail & Related papers  (2026-05-27T16:36:01Z)
• Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning [3.2641459166493405]
  We propose a novel compression method based on Reinforcement Learning applied to a T5 language model architecture.<n>This approach enables the compression of data into sequences of tokens rather than traditional vector representations.<n>By leveraging the latent information within language models, our system effectively compresses data without requiring explicit content understanding.
  arXiv  Detail & Related papers  (2026-02-12T16:30:55Z)
• Arbitrary Ratio Feature Compression via Next Token Prediction [52.10426317889982]
  Arbitrary Ratio Feature Compression (ARFC) framework supports any compression ratio with a single model.<n>ARC is an auto-regressive model that performs compression via next-gressive prediction.<n>MoS module refines the compressed tokens by utilizing multiple compression results.<n>ERGC is integrated into the training process to preserve semantic and structural relationships during compression.
  arXiv  Detail & Related papers  (2026-02-12T02:38:57Z)
• Proxy Compression for Language Modeling [58.904023114033954]
  proxy compression is an alternative training scheme that preserves the efficiency benefits of compressed inputs.<n>Experiments on code language modeling demonstrate that proxy compression substantially improves training efficiency.<n>As model scale increases, proxy-trained models eventually match or rival tokenizer approaches.
  arXiv  Detail & Related papers  (2026-02-04T07:36:46Z)
• Context Compression via Explicit Information Transmission [25.078241611630585]
  Long-context inference with Large Language Models (LLMs) is costly due to quadratic attention and growing key-value caches.<n>We propose ComprExIT, a lightweight framework that formulates soft compression into a new paradigm.
  arXiv  Detail & Related papers  (2026-02-03T17:44:12Z)
• Simple Context Compression: Mean-Pooling and Multi-Ratio Training [12.049015994907629]
  We develop a lightweight and simple mean-pooling approach that consistently outperforms the widely used compression-tokens architecture.<n>We conduct extensive experiments across in-domain and out-of-domain QA datasets, as well as across model families, scales, and compression ratios.<n>Overall, our simple mean-pooling approach achieves the strongest performance, with a relatively small drop when training for multiple compression ratios.
  arXiv  Detail & Related papers  (2025-10-23T17:57:23Z)
• Compressing Many-Shots in In-Context Learning [61.231471139896506]
  We study an approach to improve the memory and computational efficiency of ICL inference by compressing the many-shot prompts.<n>We first show that existing prompt compression methods are ineffective for many-shot compression.<n>We propose MemCom, a layer-wise compression method.
  arXiv  Detail & Related papers  (2025-10-17T16:57:42Z)
• AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation [27.480791258325066]
  We introduce AttnComp, an adaptive, efficient and context-aware compression framework.<n>AttnComp employs a Top-P compression algorithm to retain the minimal set of documents.<n>In addition to compression, AttnComp estimates response confidence by assessing the overall relevance of the retrieved content.
  arXiv  Detail & Related papers  (2025-09-22T08:18:50Z)
• UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression [86.33995240043936]
  UniGist is a sequence-level long-context compression framework for large language models.<n>It efficiently preserves context information by replacing raw tokens with special compression tokens (gists) in a fine-grained manner.<n>Our scheme also supports flexible inference by allowing the actual removal of compressed tokens, resulting in real-time memory savings.
  arXiv  Detail & Related papers  (2025-09-19T08:47:37Z)
• Hierarchical Semantic Compression for Consistent Image Semantic Restoration [62.97519327310638]
  We propose a novel hierarchical semantic compression (HSC) framework that purely operates within intrinsic semantic spaces from generative models.<n> Experimental results demonstrate that the proposed HSC framework achieves the state-of-the-art performance on subjective quality and consistency for human vision.
  arXiv  Detail & Related papers  (2025-02-24T03:20:44Z)
• ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference [61.412894960600205]
  Large Language Models (LLMs) require significant GPU memory when processing long texts.<n>ChunkKV reimagines KV cache compression by treating semantic chunks as basic compression units.<n>Result: ChunkKV outperforms state-of-the-art methods by up to 8.7% in precision.
  arXiv  Detail & Related papers  (2025-02-01T03:49:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.