Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
cs.CL, cs.AI
Submitted: 2025-05-29
Updated: 2026-11-07
Code: https://github.com/yzhangchuck/Sentinel
Terminology
Sources
- AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation
- Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
- EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation
- Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference
- GPT-4 Technical Report
- Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization
- QUITO: Accelerating Long-Context Reasoning through Query-Guided Context Compression
- Retrieval Head Mechanistically Explains Long-Context Factuality
- Less is More: Compact Clue Selection for Efficient Retrieval-Augmented Generation Reasoning
- Attention Heads of Large Language Models: A Survey
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data