Research
SABET-QA: Temporal Knowledge Graph Question Answering
arXiv:2608.20083v1 Announce Type: cross Abstract: Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle
arXiv:2608.20083v1 Announce Type: cross Abstract: Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle with multi-step queries due to single-pass reasoning pipelines. We propose SABET-QA, a framework that iteratively refines reasoning states across multiple hops via a bidirectional entity-temporal scoring mechanism and a slot-aware contextualization module that aligns question semantics with temporal KG embeddings. A differentiable working memory enables progressive hypothesis refinement, while auxiliary temporal boundaries serve as coarse supervision when available. Experiments on CronQuestions, Complex-CronQuestions, MultiTQ, and TimeQuestions demonstrate consistent improvements over strong baselines, particularly on complex multi-step temporal queries.
Related
- Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering
- AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning
- Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities
- AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models
Source: arXiv cs.AI | 2026-08-21