Cover Image

COMI: Coarse-to-fine Context Compression via Marginal Information Gain

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Jiwei, Liu, Shilei, Zhang, Zhicheng, Yuan, Yujin, Zheng, Libin, Su, Wenbo, Zheng, Bo
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction
by: Zhao, Runsong, et al.
Published: (2026)

Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Model
by: Lv, Kangtao, et al.
Published: (2026)

ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph
by: Liu, Langming, et al.
Published: (2025)

Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven
by: Tang, Jiwei, et al.
Published: (2026)

How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models
by: Lv, Kangtao, et al.
Published: (2025)

Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios
by: Tang, Jiwei, et al.
Published: (2024)

GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
by: Tang, Jiwei, et al.
Published: (2025)

PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning
by: Liu, Langming, et al.
Published: (2026)

ChineseEcomQA: A Scalable E-commerce Concept Evaluation Benchmark for Large Language Models
by: Chen, Haibin, et al.
Published: (2025)

Compressing Lengthy Context With UltraGist
by: Zhang, Peitian, et al.
Published: (2024)

Long Context Compression with Activation Beacon
by: Zhang, Peitian, et al.
Published: (2024)

Submodular Context Partitioning and Compression for In-Context Learning
by: Zheng, Shaoyi, et al.
Published: (2025)

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

DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens
by: Chen, Shaoshen, et al.
Published: (2025)

Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
by: He, Yancheng, et al.
Published: (2025)

CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
by: Zhao, Runsong, et al.
Published: (2026)

Boosting Long-Context Management via Query-Guided Activation Refilling
by: Qian, Hongjin, et al.
Published: (2024)

Fovea Transformer: Efficient Long-Context Modeling with Structured Fine-to-Coarse Attention
by: He, Ziwei, et al.
Published: (2023)

COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing
by: Sheth, Rajvee, et al.
Published: (2025)

No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization
by: Shi, Wenhang, et al.
Published: (2025)

Extending Llama-3's Context Ten-Fold Overnight
by: Zhang, Peitian, et al.
Published: (2024)

AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models
by: Zhang, Qianchi, et al.
Published: (2024)

Glyph: Scaling Context Windows via Visual-Text Compression
by: Cheng, Jiale, et al.
Published: (2025)

SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression
by: Zhang, Biao, et al.
Published: (2025)

AIR: Complex Instruction Generation via Automatic Iterative Refinement
by: Liu, Wei, et al.
Published: (2025)

AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistant
by: Zhou, Yujia, et al.
Published: (2024)

Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission
by: Ye, Jiangnan, et al.
Published: (2026)

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
by: Deng, Chenlong, et al.
Published: (2025)

PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models
by: Zheng, Haoyu, et al.
Published: (2026)

Reranking Passages with Coarse-to-Fine Neural Retriever Enhanced by List-Context Information
by: Zhu, Hongyin
Published: (2023)

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
by: Liu, Xiang, et al.
Published: (2025)

Are Long-LLMs A Necessity For Long-Context Tasks?
by: Qian, Hongjin, et al.
Published: (2024)

Grounding Language Model with Chunking-Free In-Context Retrieval
by: Qian, Hongjin, et al.
Published: (2024)

CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria
by: Hu, Xinyu, et al.
Published: (2026)

Improving Sampling for Masked Diffusion Models via Information Gain
by: Yang, Kaisen, et al.
Published: (2026)

Less Is More: Elevating RAG via Performance-Driven Context Compression
by: Cui, Ziqiang, et al.
Published: (2025)

Assessing the Efficacy of Grammar Error Correction: A Human Evaluation Approach in the Japanese Context
by: Wang, Qiao, et al.
Published: (2024)

Naive Bayes-based Context Extension for Large Language Models
by: Su, Jianlin, et al.
Published: (2024)

AIM: Asymmetric Information Masking for Visual Question Answering Continual Learning
by: Zhang, Peifeng, et al.
Published: (2026)