BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection

• URL: http://arxiv.org/abs/2603.19635v1
• Date: Fri, 20 Mar 2026 04:35:04 GMT
• Title: BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection
• Abstract summary: Existing compression methods often suffer from high training costs or semantic fragmentation due to aggressive token pruning.<n>We propose BEAVER, a novel training-free framework that shifts compression from linear token removal to structure-aware hierarchical selection.<n>We show that BEAVER achieves comparable performance to state-of-the-art (SOTA) methods like LongLLMLingua.
• Score: 21.177715869071793
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer from high training costs or semantic fragmentation due to aggressive token pruning. In this paper, we propose BEAVER, a novel training-free framework that shifts compression from linear token removal to structure-aware hierarchical selection. BEAVER maximizes hardware parallelism by mapping variable-length contexts into dense page-level tensors via dual-path pooling, and preserves discourse integrity through a hybrid planner combining semantic and lexical dual-branch selection with sentence smoothing. Extensive evaluations on four long-context benchmarks demonstrate that BEAVER achieves comparable performance to state-of-the-art (SOTA) methods like LongLLMLingua. Notably, on the RULER benchmark, BEAVER maintains high fidelity in multi-needle retrieval where baselines deteriorate. Regarding efficiency, BEAVER reduces latency by 26.4x on 128k contexts, offering a scalable solution for high-throughput applications. Our code is available at https://cslikai.cn/BEAVER/.

Related papers

• Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding [51.48425605758328]
  We present Faster Flash Decoding (FFD), a novel hardware-algorithm co-design framework designed to break the memory wall in long-context decoding.<n>FFD integrates the selector and computer into a fully fused kernel, replacing external metadata indices with content-aware scanning.<n>It achieves up to 11.6x kernel-level speedup and scaling to 256K context length, with 2.37x end-to-end throughput improvement.
  arXiv  Detail & Related papers  (2026-08-31T15:13:20Z)
• Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models [65.49950267695267]
  We introduce Omni2LoRA, a framework for efficient parametric memory compression via coherence-preserving context distillation.<n>By converting multimodal memory into a fixed-budget, reusable parameter state, our method drives answer-time multimodal-token load to zero.
  arXiv  Detail & Related papers  (2026-08-10T07:49:10Z)
• VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling [81.92510561363197]
  We introduce VLZip, a framework that unifies visual and textual compression for high-fidelity reasoning within a pure Transformer.<n>We also introduce LongVLBench, a new benchmark derived from video narratives that demands holistic, narrative-level reasoning.
  arXiv  Detail & Related papers  (2026-08-09T10:31:03Z)
• You Only Index Once: Cross-Layer Sparse Attention with Shared Routing [61.29627714699688]
  Cross-layer sparse attention (A) is built on top of KV-sharing architectures such as YOCO.<n>A single indexer computes token-level top-k selection once and reuses the resulting index across layers.<n>Results show CLSA is both accurate and efficient, achieving up to 7.6x decoding speedup and 17.1x overall throughput improvement at 128K context.
  arXiv  Detail & Related papers  (2026-06-04T17:54:04Z)
• Joint Semantic Token Selection and Prompt Optimization for Interpretable Prompt Learning [57.91658393667469]
  Interpretable Prompt Learning is a hybrid framework that alternates between discrete semantic token selection and continuous prompt optimization.<n>Our framework is plug-and-play, allowing seamless integration with existing prompt learning methods.
  arXiv  Detail & Related papers  (2026-05-06T02:38:59Z)
• Stacked from One: Multi-Scale Self-Injection for Context Window Extension [69.24689919827817]
  modelname is a novel framework based on multi-grained context compression and query-aware information acquisition.<n>modelnameachieves performance superior or comparable to strong baselines.
  arXiv  Detail & Related papers  (2026-03-05T03:16:16Z)
• CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference [9.561727872677173]
  We propose textbfCHESS, an textitalgorithm-system co-design KV-cache management system.<n>textbf1.% of the KV cache, delivers low-context stable inference with up to textbf4.56$times$ higher throughput, and consistently outperforms other strong baselines.
  arXiv  Detail & Related papers  (2026-02-24T09:54:59Z)
• Training-free Context-adaptive Attention for Efficient Long Context Modeling [57.703159205740185]
  Training-free Context-adaptive Attention (TCA-Attention) is a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference.<n>TCA-Attention achieves a 2.8$times$ speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention.
  arXiv  Detail & Related papers  (2025-12-10T01:54:57Z)
• CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning [34.38636514331703]
  CLaRa is a unified framework that performs embedding-based compression and joint optimization in a shared continuous space.<n> Experiments show that CLaRa achieves state-of-the-art compression and reranking performance, often surpassing text-based fine-tuned baselines.
  arXiv  Detail & Related papers  (2025-11-24T00:11:14Z)
• Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation [75.58269386927076]
  Autoregressive (AR) models are often dismissed as impractical due to prohibitive computational cost.<n>This work re-thinks this paradigm, introducing a framework built on hierarchical parallelism and progressive adaptation.<n> Experiments on diverse datasets (natural, satellite, medical) validate that our method achieves new state-of-the-art compression.
  arXiv  Detail & Related papers  (2025-11-14T06:27:58Z)
• 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)
• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition [95.54406667705999]
  Pangu Embedded is an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs)<n>It addresses the significant computational costs and inference latency challenges prevalent in existing reasoning-optimized LLMs.<n>It delivers rapid responses and state-of-the-art reasoning quality within a single, unified model architecture.
  arXiv  Detail & Related papers  (2025-05-28T14:03:02Z)
• Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints [14.341123057506827]
  Large Language Models (LLMs) are indispensable in today's applications, but their inference procedure demands significant computational resources.<n>This paper formulates LLM inference optimization as a multi-stage online scheduling problem.<n>We develop a fluid dynamics approximation to provide a tractable benchmark that guides algorithm design.
  arXiv  Detail & Related papers  (2025-04-15T16:00:21Z)
• TreeKV: Smooth Key-Value Cache Compression with Tree Structures [19.06842704338332]
  TreeKV is a training-free method that employs a tree structure for smooth cache compression.<n>It consistently surpasses all baseline models in language modeling tasks on PG19 and OpenWebText2.
  arXiv  Detail & Related papers  (2025-01-09T06:00:27Z)
• LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models [22.06402870816756]
  Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. This paper presents LLMLingua, a coarse-to-fine prompt compression method that involves a budget controller to maintain semantic integrity. We show that the proposed approach yields state-of-the-art performance and allows for up to 20x compression with little performance loss.
  arXiv  Detail & Related papers  (2023-10-09T14:10:21Z)

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.