Cover Image

Lost in the Evidence? Reproducing Document Position and Context Size Effects in RAG

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gabín, Jorge, Perez, Anxo, Parapar, Javier
Format:	Preprint
Published:	2026
Subjects:	Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Questions: Leveraging ColBERT for Keyphrase Search
by: Gabín, Jorge, et al.
Published: (2024)

Enhancing Automatic Keyphrase Labelling with Text-to-Text Transfer Transformer (T5) Architecture: A Framework for Keyphrase Generation and Filtering
by: Gabín, Jorge, et al.
Published: (2024)

Hybrid Pooling with LLMs via Relevance Context Learning
by: Otero, David, et al.
Published: (2026)

LLM-Assisted Pseudo-Relevance Feedback
by: Otero, David, et al.
Published: (2026)

Towards Reliable Testing for Multiple Information Retrieval System Comparisons
by: Otero, David, et al.
Published: (2025)

Limitations of Automatic Relevance Assessments with Large Language Models for Fair and Reliable Retrieval Evaluation
by: Otero, David, et al.
Published: (2024)

On the Reproducibility of Learned Sparse Retrieval Adaptations for Long Documents
by: Lionis, Emmanouil Georgios, et al.
Published: (2025)

MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG
by: Wang, Xihang, et al.
Published: (2026)

Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction
by: Qiao, Jingfen, et al.
Published: (2025)

Controlled Retrieval-augmented Context Evaluation for Long-form RAG
by: Ju, Jia-Huei, et al.
Published: (2025)

Optimizing Query Generation for Enhanced Document Retrieval in RAG
by: Koo, Hamin, et al.
Published: (2024)

Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG
by: Wang, Xihang, et al.
Published: (2026)

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

From Documents to Dialogue: Building KG-RAG Enhanced AI Assistants
by: Mukherjee, Manisha, et al.
Published: (2025)

Context Embeddings for Efficient Answer Generation in RAG
by: Rau, David, et al.
Published: (2024)

Rank4Gen: RAG-Preference-Aligned Document Set Selection and Ranking
by: Fan, Yongqi, et al.
Published: (2026)

Enhancing Technical Documents Retrieval for RAG
by: Lai, Songjiang, et al.
Published: (2025)

MHier-RAG: Multi-Modal RAG for Visual-Rich Document Question-Answering via Hierarchical and Multi-Granularity Reasoning
by: Gong, Ziyu, et al.
Published: (2025)

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

Lost in Transliteration: Bridging the Script Gap in Neural IR
by: Chari, Andreas, et al.
Published: (2025)

ECoRAG: Evidentiality-guided Compression for Long Context RAG
by: Jeong, Yeonseok, et al.
Published: (2025)

Separating Semantic Competition from Context Length in RAG Reading
by: Repantis, Vyzantinos, et al.
Published: (2026)

Balancing Content Size in RAG-Text2SQL System
by: Gurawa, Prakhar, et al.
Published: (2025)

LURE-RAG: Lightweight Utility-driven Reranking for Efficient RAG
by: Chandra, Manish, et al.
Published: (2026)

Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis
by: Bhat, Sinchana Ramakanth, et al.
Published: (2025)

Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Bias
by: Iratni, Malika, et al.
Published: (2025)

RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
by: Han, Haoyu, et al.
Published: (2025)

BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs
by: Pan, Duyi, et al.
Published: (2026)

Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG
by: Terrenzi, Riccardo, et al.
Published: (2026)

Reproducing and Comparing Distillation Techniques for Cross-Encoders
by: Morand, Victor, et al.
Published: (2026)

Reproducing Adaptive Reranking for Reasoning-Intensive IR
by: Rathee, Mandeep, et al.
Published: (2026)

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

TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems
by: Jiang, Xinke, et al.
Published: (2024)

EnronQA: Towards Personalized RAG over Private Documents
by: Ryan, Michael J., et al.
Published: (2025)

KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG
by: Huang, Yiqian, et al.
Published: (2025)

Document Set Expansion with Positive-Unlabelled Learning Using Intractable Density Estimation
by: Zhang, Haiyang, et al.
Published: (2024)

A Reproducibility Study of Metacognitive Retrieval-Augmented Generation
by: Iturra-Bocaz, Gabriel, et al.
Published: (2026)

Cold-Starts in Generative Recommendation: A Reproducibility Study
by: Zhang, Zhen, et al.
Published: (2026)

Revisiting Document-Level Relation Extraction with Context-Guided Link Prediction
by: Jain, Monika, et al.
Published: (2024)

Reproducing NevIR: Negation in Neural Information Retrieval
by: Elsen, Coen van den, et al.
Published: (2025)