Imagen de Portada

A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cuconasu, Florin, Trappolini, Giovanni, Tonellotto, Nicola, Silvestri, Fabrizio
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Information Retrieval
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Power of Noise: Redefining Retrieval for RAG Systems
por: Cuconasu, Florin, et al.
Publicado: (2024)

RRAML: Reinforced Retrieval Augmented Machine Learning
por: Bacciu, Andrea, et al.
Publicado: (2023)

Redefining Retrieval Evaluation in the Era of LLMs
por: Trappolini, Giovanni, et al.
Publicado: (2025)

Do RAG Systems Really Suffer From Positional Bias?
por: Cuconasu, Florin, et al.
Publicado: (2025)

ECLIPSE: Contrastive Dimension Importance Estimation with Pseudo-Irrelevance Feedback for Dense Retrieval
por: D'Erasmo, Giulio, et al.
Publicado: (2024)

The Distracting Effect: Understanding Irrelevant Passages in RAG
por: Amiraz, Chen, et al.
Publicado: (2025)

A Reproducible Analysis of Sequential Recommender Systems
por: Betello, Filippo, et al.
Publicado: (2024)

Multimodal Neural Databases
por: Trappolini, Giovanni, et al.
Publicado: (2023)

A Reproducibility Study of PLAID
por: MacAvaney, Sean, et al.
Publicado: (2024)

ClaimTrust: Propagation Trust Scoring for RAG Systems
por: Qian, Hangkai, et al.
Publicado: (2025)

Efficient Constant-Space Multi-Vector Retrieval
por: MacAvaney, Sean, et al.
Publicado: (2025)

Integrating Item Relevance in Training Loss for Sequential Recommender Systems
por: Bacciu, Andrea, et al.
Publicado: (2023)

Static Pruning in Dense Retrieval using Matrix Decomposition
por: Siciliano, Federico, et al.
Publicado: (2024)

A Theoretical Analysis of Recommendation Loss Functions under Negative Sampling
por: Di Teodoro, Giulia, et al.
Publicado: (2024)

Generating Query Recommendations via LLMs
por: Bacciu, Andrea, et al.
Publicado: (2024)

Graph Neural Re-Ranking via Corpus Graph
por: Di Francesco, Andrea Giuseppe, et al.
Publicado: (2024)

Trust or Abstain? A Self-Aware RAG Approach
por: Zhu, Xi, et al.
Publicado: (2026)

A Picture of Agentic Search
por: Pezzuti, Francesca, et al.
Publicado: (2026)

DistRAG: Towards Distance-Based Spatial Reasoning in LLMs
por: Schneider, Nicole R, et al.
Publicado: (2025)

Evaluating Factual Density in Multi-Source RAG: A Study in Medical AI Accuracy
por: DeMarco, Michael R.
Publicado: (2026)

CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction
por: Maheshwari, Harsh, et al.
Publicado: (2025)

AMAQA: A Metadata-based QA Dataset for RAG Systems
por: Bruni, Davide, et al.
Publicado: (2025)

MURR: Model Updating with Regularized Replay for Searching a Document Stream
por: Yang, Eugene, et al.
Publicado: (2025)

Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers
por: Sawarkar, Kunal, et al.
Publicado: (2024)

Evaluating the Efficacy of Open-Source LLMs in Enterprise-Specific RAG Systems: A Comparative Study of Performance and Scalability
por: B, Gautam, et al.
Publicado: (2024)

Statistical Foundations of DIME: Risk Estimation for Practical Index Selection
por: D'Erasmo, Giulio, et al.
Publicado: (2026)

MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering
por: Ning, Yingpeng, et al.
Publicado: (2025)

Vector RAG vs LLM-Compiled Wiki: A Preregistered Comparison on a Small Multi-Domain Research
por: Cochran, Theodore O.
Publicado: (2026)

A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning
por: Yuan, Ye, et al.
Publicado: (2024)

Knowledge in Triples for LLMs: Enhancing Table QA Accuracy with Semantic Extraction
por: Sholehrasa, Hossein, et al.
Publicado: (2024)

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

Political Events using RAG with LLMs
por: Arslan, Muhammad, et al.
Publicado: (2025)

RAG based Question-Answering for Contextual Response Prediction System
por: Veturi, Sriram, et al.
Publicado: (2024)

LiveRAG: A diverse Q&A dataset with varying difficulty level for RAG evaluation
por: Carmel, David, et al.
Publicado: (2025)

Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG
por: Khadilkar, Harshad, et al.
Publicado: (2025)

FIT-RAG: Black-Box RAG with Factual Information and Token Reduction
por: Mao, Yuren, et al.
Publicado: (2024)

LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval
por: Kabir, Muhammad Rafsan, et al.
Publicado: (2025)

MedCoT-RAG: Causal Chain-of-Thought RAG for Medical Question Answering
por: Wang, Ziyu, et al.
Publicado: (2025)

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

Evidence Contextualization and Counterfactual Attribution for Conversational QA over Heterogeneous Data with RAG Systems
por: Roy, Rishiraj Saha, et al.
Publicado: (2024)