Image de couverture de livre

From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Akarsu, Meftun, Karaman, Recep Kaan, Mierbach, Christopher
Format:	Preprint
Publié:	2026
Sujets:	Information Retrieval Computation and Language H.3.3, H.3.4
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LLM-Assisted Relevance Assessments: When Should We Ask LLMs for Help?
par: Takehi, Rikiya, et autres
Publié: (2024)

flexvec: SQL Vector Retrieval with Programmatic Embedding Modulation
par: Delmas, Damian
Publié: (2026)

The Treatment of Ties in Rank-Biased Overlap
par: Corsi, Matteo, et autres
Publié: (2024)

Diversification as Risk Minimization
par: Takehi, Rikiya, et autres
Publié: (2025)

EnterpriseRAG-Bench: A RAG Benchmark for Company Internal Knowledge
par: Sun, Yuhong, et autres
Publié: (2026)

Stop Using the Wilcoxon Test: Myth, Misconception and Misuse in IR Research
par: Urbano, Julián
Publié: (2026)

Behavior-Aware Dual-Channel Preference Learning for Heterogeneous Sequential Recommendation
par: Xiao, Jing, et autres
Publié: (2026)

PeakNetFP: Peak-based Neural Audio Fingerprinting Robust to Extreme Time Stretching
par: Cortès-Sebastià, Guillem, et autres
Publié: (2025)

AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference
par: Deng, Yangshen, et autres
Publié: (2025)

Siren Federate: Bridging document, relational, and graph models for exploratory graph analysis
par: Bordea, Georgeta, et autres
Publié: (2025)

Passing the Baton: High Throughput Distributed Disk-Based Vector Search with BatANN
par: Dang, Nam Anh, et autres
Publié: (2025)

Beyond Similarity Search: A Unified Data Layer for Production RAG Systems
par: Budigi, Venkata Krishna Prasanth, et autres
Publié: (2026)

A Recommender System Based on Binary Matrix Representations for Cognitive Disorders
par: Kutil, Raoul H., et autres
Publié: (2025)

MIRA: An LLM-Assisted Benchmark for Multi-Category Integrated Retrieval
par: Türkmen, Mehmet Deniz, et autres
Publié: (2026)

AuthorityBench: Benchmarking LLM Authority Perception for Reliable Retrieval-Augmented Generation
par: Yao, Zhihui, et autres
Publié: (2026)

Doc2Query++: Topic-Coverage based Document Expansion and its Application to Dense Retrieval via Dual-Index Fusion
par: Kuo, Tzu-Lin, et autres
Publié: (2025)

Improving BM25 Code Retrieval Under Fixed Generic Tokenization: Adaptive q-Log Odds as a Drop-In BM25 Fix
par: Radha, Santosh Kumar, et autres
Publié: (2026)

Information Retrieval for Climate Impact
par: de Rijke, Maarten, et autres
Publié: (2025)

Relevance Filtering for Embedding-based Retrieval
par: Rossi, Nicholas, et autres
Publié: (2024)

An Intrinsic Framework of Information Retrieval Evaluation Measures
par: Giner, Fernando
Publié: (2023)

Enhancing Relevance of Embedding-based Retrieval at Walmart
par: Lin, Juexin, et autres
Publié: (2024)

Improving E-commerce Search with Category-Aligned Retrieval
par: Aliev, Rauf
Publié: (2025)

Reverse-Engineering the Retrieval Process in GenIR Models
par: Reusch, Anja, et autres
Publié: (2025)

Dynamic Superblock Pruning for Fast Learned Sparse Retrieval
par: Carlson, Parker, et autres
Publié: (2025)

Beyond the Geometric Curse: High-Dimensional N-Gram Hashing for Dense Retrieval
par: Sharma, Sangeet
Publié: (2026)

ESANS: Effective and Semantic-Aware Negative Sampling for Large-Scale Retrieval Systems
par: Xing, Haibo, et autres
Publié: (2025)

Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality
par: Feng, Naihe, et autres
Publié: (2025)

CSMF: Cascaded Selective Mask Fine-Tuning for Multi-Objective Embedding-Based Retrieval
par: Deng, Hao, et autres
Publié: (2025)

A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models
par: Kankanampati, Yash, et autres
Publié: (2026)

Text-like Encoding of Collaborative Information in Large Language Models for Recommendation
par: Zhang, Yang, et autres
Publié: (2024)

SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables
par: Park, Sungho, et autres
Publié: (2026)

RAD-DPO: Robust Adaptive Denoising Direct Preference Optimization for Generative Retrieval in E-commerce
par: Chen, Zhiguo, et autres
Publié: (2026)

KamerRaad: Enhancing Information Retrieval in Belgian National Politics through Hierarchical Summarization and Conversational Interfaces
par: Rogiers, Alexander, et autres
Publié: (2024)

Explainable Graph-based Search for Lessons-Learned Documents in the Semiconductor Industry
par: Abu-Rasheed, Hasan, et autres
Publié: (2021)

Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction
par: Srinivasan, Akshay Govind, et autres
Publié: (2025)

Diagnosing LLM-based Rerankers in Cold-Start Recommender Systems: Coverage, Exposure and Practical Mitigations
par: Lemdiasova, Ekaterina, et autres
Publié: (2026)

SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation
par: Akay, Yagiz Can, et autres
Publié: (2026)

From Item-Only to Query-Item: Query-Conditioned Generative Search with QGS in Quark
par: Song, Yanglong, et autres
Publié: (2026)

Leveraging LLMs to Enable Natural Language Search on Go-to-market Platforms
par: Yao, Jesse, et autres
Publié: (2024)

Deep Recommender Models Inference: Automatic Asymmetric Data Flow Optimization
par: Ruggeri, Giuseppe, et autres
Publié: (2025)