paper-with-me

홈 › Papers

DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens

2025-02-17 · Shaoshen Chen, Yangning Li, Zishan Xu, Yinghui Li, Xin Su, Zifei Shan, Hai-Tao Zheng

Large Language Models (LLMs) face computational inefficiencies and redundant processing when handling long context inputs, prompting a focus on compression techniques. While existing semantic vector-based compression methods achieve promising performance, these methods fail to account for the intrinsic information density variations between context chunks, instead allocating soft tokens uniformly across context chunks. This uniform distribution inevitably diminishes allocation to information-critical regions. To address this, we propose Dynamic Allocation of Soft Tokens (DAST), a simple yet effective method that leverages the LLM's intrinsic understanding of contextual relevance to guide compression. DAST combines perplexity-based local information with attention-driven global information to dynamically allocate soft tokens to the informative-rich chunks, enabling effective, context-aware compression. Experimental results across multiple benchmarks demonstrate that DAST surpasses state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2502.11493

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

AdaSTORM: Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaboration

2026-06-15 · Bing Hao, Ruijie Wang, Haodong Qian, Yunlong Chu 외 arxiv

Large Language Models (LLMs) demonstrate remarkable potential in dynamic graph reasoning, but suffer from a scaling bottleneck: current models can only handle graphs with tens of nodes, constrained by exponential reasoni…

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

2026-03-26 · Yijiong Yu, Shuai Yuan, Jie Zheng, Huazheng Wang 외 arxiv

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 rati…

ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs

2026-02-03 · Xuancheng Li, Haitao Li, Yujia Zhou, Qingyao Ai 외 arxiv

Long-context inputs in large language models (LLMs) often suffer from the "lost in the middle" problem, where critical information becomes diluted or ignored due to excessive length. Context compression methods aim to ad…

DAST: Difficulty-Aware Self-Training on Large Language Models

2025-03-12 · Boyang Xue, Qi Zhu, Hongru Wang, Rui Wang 외

Present Large Language Models (LLM) self-training methods always under-sample on challenging queries, leading to inadequate learning on difficult problems which limits LLMs' ability. Therefore, this work proposes a diffi…

Data Augmentation

PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction

2026-03-20 · Runsong Zhao, Shilei Liu, Jiwei Tang, Langming Liu 외 arxiv

While context compression can mitigate the growing inference costs of Large Language Models (LLMs) by shortening contexts, existing methods that specify a target compression ratio or length suffer from unpredictable perf…