Cover Image

AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luo, Lvzhou, Cao, Yixuan, Luo, Ping
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

Attention with Dependency Parsing Augmentation for Fine-Grained Attribution
by: Ding, Qiang, et al.
Published: (2024)

LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning
by: Ji, Mengmeng, et al.
Published: (2026)

Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs
by: Zeng, Shenglai, et al.
Published: (2026)

The Gray Zone of Faithfulness: Taming Ambiguity in Unfaithfulness Detection
by: Ding, Qiang, et al.
Published: (2025)

Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA
by: Li, Zhanli, et al.
Published: (2026)

DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search
by: Li, Zhanli, et al.
Published: (2026)

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

ProxyAttn: Guided Sparse Attention via Representative Heads
by: Wang, Yixuan, et al.
Published: (2025)

AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation
by: Fang, Yixiong, et al.
Published: (2025)

Context-Adaptive Synthesis and Compression for Enhanced Retrieval-Augmented Generation in Complex Domains
by: Zhou, Peiran, et al.
Published: (2025)

$Δ$-AttnMask: Attention-Guided Masked Hidden States for Efficient Data Selection and Augmentation
by: Hu, Jucheng, et al.
Published: (2025)

CompLLM: Compression for Long Context Q&A
by: Berton, Gabriele, et al.
Published: (2025)

Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts
by: Kim, Youna, et al.
Published: (2024)

SpecAttn: Speculating Sparse Attention
by: Shah, Harsh
Published: (2025)

CompAct: Compressing Retrieved Documents Actively for Question Answering
by: Yoon, Chanwoong, et al.
Published: (2024)

Reasoning Pattern Matters: Learning to Reason without Human Rationales
by: Pang, Chaoxu, et al.
Published: (2025)

Influence Guided Context Selection for Effective Retrieval-Augmented Generation
by: Deng, Jiale, et al.
Published: (2025)

Comp-Attn: Present-and-Align Attention for Compositional Video Generation
by: Zhang, Hongyu, et al.
Published: (2025)

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
by: Wang, Zijun, et al.
Published: (2024)

ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation
by: Yao, Ruobing, et al.
Published: (2025)

Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
by: Zhu, Yun, et al.
Published: (2024)

SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
by: Jin, Yiqiao, et al.
Published: (2025)

EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation
by: Hwang, Taeho, et al.
Published: (2024)

MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
by: Tang, Yixuan, et al.
Published: (2024)

Uncovering Limitations of Large Language Models in Information Seeking from Tables
by: Pang, Chaoxu, et al.
Published: (2024)

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation
by: Yao, Zijun, et al.
Published: (2024)

AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation
by: Guo, Yilin, et al.
Published: (2026)

ICA-RAG: Information Completeness Guided Adaptive Retrieval-Augmented Generation for Disease Diagnosis
by: He, Jiawei, et al.
Published: (2025)

Retrieval Augmented Generation using Engineering Design Knowledge
by: Siddharth, L., et al.
Published: (2023)

AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache
by: Song, Dinghong, et al.
Published: (2025)

ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting
by: Tian, Yuxing, et al.
Published: (2026)

Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation
by: Belikova, Julia, et al.
Published: (2026)

Guideline Learning for In-context Information Extraction
by: Pang, Chaoxu, et al.
Published: (2023)

Inference Scaling for Long-Context Retrieval Augmented Generation
by: Yue, Zhenrui, et al.
Published: (2024)

LongAttn: Selecting Long-context Training Data via Token-level Attention
by: Wu, Longyun, et al.
Published: (2025)

Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
by: Gao, Sensen, et al.
Published: (2025)

ConfRAG: Confidence-Guided Retrieval-Augmenting Generation
by: Huang, Yin, et al.
Published: (2025)

The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
by: Kahardipraja, Patrick, et al.
Published: (2025)

Document-Level Tabular Numerical Cross-Checking: A Coarse-to-Fine Approach
by: Pang, Chaoxu, et al.
Published: (2025)

BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models
by: Luo, Kun, et al.
Published: (2024)