On ChemKGMultiHopQA, iterative retrieval-reasoning outperformed oracle gold-context static RAG for all 11 LLMs tested, with gains up to 25.6 percentage points.
Jinyu Wang, Jingjing Fu, Rui Wang, Lei Song, and Jiang Bian
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
ArchRAG proposes attributed-community hierarchical indexing and LLM clustering to improve accuracy and lower token usage in graph-based retrieval-augmented generation.
A full-paper multimodal knowledge-graph pipeline with a GRPO-trained 4B extractor and tri-source agent CLI reports improved multi-hop scientific reasoning, alongside a released one-million-paper knowledge graph.
Presents RegOps-Bench benchmark and RefWalk framework for citation-closure retrieval and per-rule attribution in regulatory compliance QA, reporting substantial gains in recall and citation accuracy over baselines.
citing papers explorer
-
When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
On ChemKGMultiHopQA, iterative retrieval-reasoning outperformed oracle gold-context static RAG for all 11 LLMs tested, with gains up to 25.6 percentage points.
-
ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation
ArchRAG proposes attributed-community hierarchical indexing and LLM clustering to improve accuracy and lower token usage in graph-based retrieval-augmented generation.
-
Agents-K1: Towards Agent-native Knowledge Orchestration
A full-paper multimodal knowledge-graph pipeline with a GRPO-trained 4B extractor and tri-source agent CLI reports improved multi-hop scientific reasoning, alongside a released one-million-paper knowledge graph.
-
Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering
Presents RegOps-Bench benchmark and RefWalk framework for citation-closure retrieval and per-rule attribution in regulatory compliance QA, reporting substantial gains in recall and citation accuracy over baselines.