Research map / Graph learning / Knowledge and temporal graphs
NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA
Hyeong Kyu Choi, Seunghun Lee, Jaewon Chu, Hyunwoo J. Kim
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 |
|---|---|---|---|
| remove the Backup step (ablation) | NuTrea · WebQSP | H@1: 77.4 -> 74.8 | Hurt |
| remove the Backup step (ablation) | NuTrea · WebQSP | F1: 72.7 -> 70.4 | Hurt |
| remove RF-IEF node embedding (use averaged relation embeddings) (ablation) | NuTrea · WebQSP | H@1: 77.4 -> 76.8 | Hurt |
| remove RF-IEF node embedding (ablation) | NuTrea · WebQSP | F1: 72.7 -> 71.5 | Hurt |
| remove both Backup and RF-IEF (ablation) | NuTrea · WebQSP | H@1: 77.4 -> 73.4 | Hurt |
| remove both Backup and RF-IEF (ablation) | NuTrea · WebQSP | F1: 72.7 -> 70.9 | Hurt |
| remove Backup alone vs removing RF-IEF alone (ablation) | NuTrea · WebQSP | H@1: 76.8 vs 74.8 | Improved |
| use NuTrea instead of ReaRev | NuTrea · WebQSP | H@1: 76.4 -> 77.4 | Improved |
| use NuTrea instead of ReaRev | NuTrea · WebQSP | F1: 70.9 -> 72.7 | Improved |
| use NuTrea instead of ReaRev | NuTrea · CWQ | H@1: 52.9 -> 53.6 | Improved |
| use NuTrea instead of TERP | NuTrea · MetaQA | avg H@1: 98.6 -> 98.8 | No clear effect |
| use NuTrea instead of ReaRev with 10% KG triplets | NuTrea · WebQSP incomplete KG (10%) | H@1: 19.4 -> 18.9 | Hurt |
Closest papers by meaning
- Question Calibration and Multi-Hop Modeling for Temporal Question Answering (AAAI 2024 · similarity 0.91)
- KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering (NeurIPS 2026 · similarity 0.90)
- Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering (AAAI 2025 · similarity 0.89)
- Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking (NeurIPS 2025 · similarity 0.89)
- Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models (AAAI 2025 · similarity 0.88)
- Tree-of-Reasoning Question Decomposition for Complex Question Answering with Large Language Models (AAAI 2024 · 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.
