Research map / Large language models / Retrieval and knowledge
SAR: A Structure-Aligned Reasoning Framework for Temporal Knowledge Graph Question Answering
Qianyi Hu, Jiaxue Liu, Xinhui Tu, Shoujin 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 structured query decomposition (ablation) | SAR (GPT-4.1) · MultiTQ overall | Hits@1: 71.1 -> 78.2 | Improved |
| add structured query decomposition (ablation) | SAR (GPT-4.1) · MultiTQ multiple-constraint | Hits@1: 37.9 -> 50.0 | Improved |
| add iterative answer verification (ablation) | SAR (GPT-4.1) · MultiTQ overall | Hits@1: 77.0 -> 78.2 | Improved |
| add iterative answer verification (ablation) | SAR (GPT-4.1) · MultiTQ time answers | Hits@1: 90.4 -> 91.5 (SAR) vs w/o decompose 92.7 | Hurt |
| increase retrieved facts K from 5 to 15 (ablation) | SAR · MultiTQ | Hits@1: approx 74% -> 78% | Improved |
| increase K from 15 to 30 (ablation) | SAR · MultiTQ | Hits@1 | No clear effect |
| allow more than 2 verification iterations (ablation) | SAR · MultiTQ | Hits@1 | No clear effect |
| use SAR instead of TempAgent | GPT-4.1 · MultiTQ overall | Hits@1: 60.7 -> 78.2 | Improved |
| use SAR instead of TempAgent | GPT-3.5 · CronQuestions overall | Hits@1: 76.7 -> 80.0 | Improved |
Closest papers by meaning
- Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation (AAAI 2025 · similarity 0.90)
- Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models (AAAI 2025 · similarity 0.90)
- Graph Reasoning Transformers for Knowledge-Aware Question Answering (AAAI 2024 · similarity 0.89)
- Reasoning of Large Language Models over Knowledge Graphs with Super-Relations (ICLR 2025 · similarity 0.89)
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.89)
- Question Calibration and Multi-Hop Modeling for Temporal Question Answering (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.
