State of RAG

Top papers

• KohakuRAG: A simple RAG framework with hierarchical document indexing(8.0)
• FLANS at SemEval-2026 Task 7: RAG with Open-Sourced Smaller LLMs for Everyday Knowledge Across Diverse Languages and Cultures(8.0)
• INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimation(7.0)
• A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity(7.0)
• Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis(7.0)
• TopoChunker: Topology-Aware Agentic Document Chunking Framework(7.0)
• Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment(7.0)
• InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context(7.0)
• SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation(7.0)
• Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval(7.0)
• HugRAG: Hierarchical Causal Knowledge Graph Design for RAG(5.0)
• Revisiting RAG Retrievers: An Information Theoretic Benchmark(5.0)
• Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG(4.0)
• AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations(3.0)