Improving Contextual Retrieval for Long Documents using Semantic Chunking and Hybrid Retrieval Strategies
cs.IR, cs.CL, cs.LG
Submitted: 2026-08-19
Updated: 2026-08-19
Terminology
Sources
- MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
- LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering
- HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
- HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction
- The Faiss library
- Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval
- Homoclinic Floer homology via direct limits
- SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation
- HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation
- UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph
Related papers
- UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA