Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Shaoshen, Li, Yangning, Xu, Zishan, Li, Yinghui, Su, Xin, Shan, Zifei, Zheng, Hai-tao
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
by: Li, Yangning, et al.
Published: (2025)

Loss-Aware Curriculum Learning for Chinese Grammatical Error Correction
by: Zhang, Ding, et al.
Published: (2024)

Correct Like Humans: Progressive Learning Framework for Chinese Text Error Correction
by: Li, Yinghui, et al.
Published: (2023)

From Token to Line: Enhancing Code Generation with a Long-Term Perspective
by: Lu, Tingwei, et al.
Published: (2025)

Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning
by: Li, Yangning, et al.
Published: (2025)

MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning
by: Li, Yangning, et al.
Published: (2025)

CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction
by: Ye, Jingheng, et al.
Published: (2024)

Embracing Ambiguity: Improving Similarity-oriented Tasks with Contextual Synonym Knowledge
by: Li, Yangning, et al.
Published: (2022)

From Retrieval to Generation: Efficient and Effective Entity Set Expansion
by: Huang, Shulin, et al.
Published: (2023)

SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging
by: Wu, Shunlong, et al.
Published: (2026)

When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models
by: Li, Yinghui, et al.
Published: (2024)

CTkvr: KV Cache Retrieval for Long-Context LLMs via Centroid then Token Indexing
by: Lu, Kuan, et al.
Published: (2025)

Automatic Context Pattern Generation for Entity Set Expansion
by: Li, Yinghui, et al.
Published: (2022)

RAISE: Reinforced Adaptive Instruction Selection For Large Language Models
by: Lv, Qingsong, et al.
Published: (2025)

Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio
by: Yu, Yijiong, et al.
Published: (2026)

Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking
by: Li, Yinghui, et al.
Published: (2023)

Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansion
by: Wang, Hebin, et al.
Published: (2024)

DAST: Difficulty-Aware Self-Training on Large Language Models
by: Xue, Boyang, et al.
Published: (2025)

SlimRAG: Retrieval without Graphs via Entity-Aware Context Selection
by: Zhang, Jiale, et al.
Published: (2025)

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
by: Zhou, Xiabin, et al.
Published: (2024)

UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entities
by: Li, Yangning, et al.
Published: (2024)

On the (In)Effectiveness of Large Language Models for Chinese Text Correction
by: Li, Yinghui, et al.
Published: (2023)

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent
by: Li, Yangning, et al.
Published: (2024)

Adapting LLMs for Efficient Context Processing through Soft Prompt Compression
by: Wang, Cangqing, et al.
Published: (2024)

ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs
by: Li, Xuancheng, et al.
Published: (2026)

Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction
by: Li, Yinghui, et al.
Published: (2024)

Mitigating Catastrophic Forgetting in Multi-domain Chinese Spelling Correction by Multi-stage Knowledge Transfer Framework
by: Xing, Peng, et al.
Published: (2024)

Compression Represents Intelligence Linearly
by: Huang, Yuzhen, et al.
Published: (2024)

ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions
by: Ye, Jingheng, et al.
Published: (2024)

Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities
by: Kuang, Jiayi, et al.
Published: (2025)

Refine Knowledge of Large Language Models via Adaptive Contrastive Learning
by: Li, Yinghui, et al.
Published: (2025)

Read As Human: Compressing Context via Parallelizable Close Reading and Skimming
by: Tang, Jiwei, et al.
Published: (2026)

Revisiting Classification Taxonomy for Grammatical Errors
by: Zou, Deqing, et al.
Published: (2025)

Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark
by: Xu, Zhikun, et al.
Published: (2024)

TokenSkip: Controllable Chain-of-Thought Compression in LLMs
by: Xia, Heming, et al.
Published: (2025)

One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs
by: Li, Yinghui, et al.
Published: (2025)

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
by: Wu, Wei, et al.
Published: (2024)

EvoConfig: Self-Evolving Multi-Agent Systems for Efficient Autonomous Environment Configuration
by: Guo, Xinshuai, et al.
Published: (2026)

Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
by: Liu, Xin, et al.
Published: (2025)

COMI: Coarse-to-fine Context Compression via Marginal Information Gain
by: Tang, Jiwei, et al.
Published: (2026)