AI Paper Atlas

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

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add structured query decomposition (ablation)SAR (GPT-4.1) · MultiTQ overallHits@1: 71.1 -> 78.2Improved
add structured query decomposition (ablation)SAR (GPT-4.1) · MultiTQ multiple-constraintHits@1: 37.9 -> 50.0Improved
add iterative answer verification (ablation)SAR (GPT-4.1) · MultiTQ overallHits@1: 77.0 -> 78.2Improved
add iterative answer verification (ablation)SAR (GPT-4.1) · MultiTQ time answersHits@1: 90.4 -> 91.5 (SAR) vs w/o decompose 92.7Hurt
increase retrieved facts K from 5 to 15 (ablation)SAR · MultiTQHits@1: approx 74% -> 78%Improved
increase K from 15 to 30 (ablation)SAR · MultiTQHits@1No clear effect
allow more than 2 verification iterations (ablation)SAR · MultiTQHits@1No clear effect
use SAR instead of TempAgentGPT-4.1 · MultiTQ overallHits@1: 60.7 -> 78.2Improved
use SAR instead of TempAgentGPT-3.5 · CronQuestions overallHits@1: 76.7 -> 80.0Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy