Imagen de Portada

How Retrieved Context Shapes Internal Representations in RAG

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yeh, Samuel, Li, Sharon
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
por: Yeh, Samuel, et al.
Publicado: (2025)

Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment
por: Yeh, Samuel, et al.
Publicado: (2025)

Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models
por: Zhang, Xuanming, et al.
Publicado: (2025)

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
por: Zhang, Xuanming, et al.
Publicado: (2025)

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

OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning
por: Zhou, Jiawei, et al.
Publicado: (2025)

HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic Representations
por: Cao, Linxiao, et al.
Publicado: (2025)

FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
por: Zhang, Qinggang, et al.
Publicado: (2025)

Retrieval or Representation? Reassessing Benchmark Gaps in Multilingual and Visually Rich RAG
por: Asenov, Martin, et al.
Publicado: (2026)

DECOR: Auditing LLM Deception via Information Manipulation Theory
por: Cai, Linyue, et al.
Publicado: (2026)

UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation
por: Li, Zixuan, et al.
Publicado: (2024)

How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs
por: Adarsh, Shivam, et al.
Publicado: (2026)

Context Shapes LLMs Retrieval-Augmented Fact-Checking Effectiveness
por: Bernardelle, Pietro, et al.
Publicado: (2026)

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

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

Context-Guided Dynamic Retrieval for Improving Generation Quality in RAG Models
por: He, Jacky, et al.
Publicado: (2025)

Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection
por: Chen, Yiwen, et al.
Publicado: (2026)

KohakuRAG: A simple RAG framework with hierarchical document indexing
por: Yeh, Shih-Ying, et al.
Publicado: (2026)

ExpertRAG: Efficient RAG with Mixture of Experts -- Optimizing Context Retrieval for Adaptive LLM Responses
por: Gumaan, Esmail
Publicado: (2025)

HyperRAG: Reasoning N-ary Facts over Hypergraphs for Retrieval Augmented Generation
por: Lien, Wen-Sheng, et al.
Publicado: (2026)

ContextRAG: Extraction-Free Hierarchical Graph Construction for Retrieval-Augmented Generation
por: Prosvirnin, Roman, et al.
Publicado: (2026)

MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation
por: Chang, Chia-Yuan, et al.
Publicado: (2024)

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

CoCR-RAG: Enhancing Retrieval-Augmented Generation in Web Q&A via Concept-oriented Context Reconstruction
por: Shi, Kaize, et al.
Publicado: (2026)

LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering
por: Zhao, Qingfei, et al.
Publicado: (2024)

L-RAG: Balancing Context and Retrieval with Entropy-Based Lazy Loading
por: Voloshyn, Sergii
Publicado: (2026)

Toward Optimal Search and Retrieval for RAG
por: Leto, Alexandria, et al.
Publicado: (2024)

EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation
por: Yao, Ruobing, et al.
Publicado: (2025)

MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
por: Qian, Hongjin, et al.
Publicado: (2024)

FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented Generation
por: Wang, Shuai, et al.
Publicado: (2024)

MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation
por: Hsiao, Chi-Hsiang, et al.
Publicado: (2025)

Long Context vs. RAG for LLMs: An Evaluation and Revisits
por: Li, Xinze, et al.
Publicado: (2024)

Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG
por: Li, Bo, et al.
Publicado: (2025)

Long$^2$RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall
por: Qi, Zehan, et al.
Publicado: (2024)

FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
por: Zhao, Xinping, et al.
Publicado: (2024)

SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval
por: Li, Jiatao, et al.
Publicado: (2024)

Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
por: Gur-Arieh, Yoav, et al.
Publicado: (2025)

What Language(s) Does Aya-23 Think In? How Multilinguality Affects Internal Language Representations
por: Trinley, Katharina, et al.
Publicado: (2025)

Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
por: Chen, Yihang, et al.
Publicado: (2026)

xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
por: Cheng, Xin, et al.
Publicado: (2024)