Research map / Large language models / Retrieval and knowledge
DCTR: Dual-Constraint Subgraph Optimization for Knowledge Graph-based Retrieval-Augmented Generation
Yukun Cao, Zirui Xu, Dongyang Li, Zhihao Guo, Luobin Huang, Lisheng Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add upper-bound path P_upper (ablation) | DCTR · WebQSP | Macro-F1: 70.33 -> 72.13 | Improved |
| add lower-bound path P_lower (ablation) | DCTR · CWQ | Macro-F1: 46.92 -> 50.12 | Improved |
| add DSRS ranking loss (ablation) | DCTR + Llama3.1-8B · WebQSP | Macro-F1: 65.73 -> 72.13 | Improved |
| add DSRS ranking loss (ablation) | DCTR retriever · CWQ | GPT-4o triple recall: 0.820 -> 0.839 | Improved |
| add P_lower (ablation) | DCTR retriever · WebQSP | path triple recall: 0.851 -> 0.890 | Improved |
| replace SubgraphRAG retrieval with DCTR (8B) | Llama3.1-8B · WebQSP-sub | Macro-F1: 71.92 -> 73.85 | Improved |
| replace SubgraphRAG retrieval with DCTR (70B) | Llama3.1-70B · CWQ-sub | Macro-F1: 60.39 -> 63.27 | Improved |
| DCTR 8B vs GNN-RAG (fine-tuned) | Llama3.1-8B · CWQ | Macro-F1: 59.4 -> 50.12 | Hurt |
| cross-dataset transfer (train on other dataset) | DCTR + 8B · CWQ | Macro-F1: 50.12 -> 38.92 | Hurt |
| cross-dataset transfer (train on other dataset) | DCTR + 8B · WebQSP | Macro-F1: 72.13 -> 67.52 | Hurt |
Closest papers by meaning
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.92)
- Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation (ICLR 2025 · similarity 0.90)
- A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented Generation (AAAI 2025 · similarity 0.90)
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation (NeurIPS 2025 · similarity 0.89)
- Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? (NeurIPS 2025 · similarity 0.88)
- Reasoning of Large Language Models over Knowledge Graphs with Super-Relations (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
