Qianyi Hu — accepted AI-conference papers

2026

SAR: A Structure-Aligned Reasoning Framework for Temporal Knowledge Graph Question Answering

Qianyi Hu, Jiaxue Liu, Xinhui Tu, Shoujin Wang

AAAI 2026technical

Large language models (LLMs) augmented with retrieval have shown impressive performance in open-domain question answering, yet struggle significantly with temporal knowledge graph question answering (TKGQA). The core issue lies in structural misalignment: treating structured, temporally sensitive gr

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Time-aware ReAct Agent for Temporal Knowledge Graph Question Answering

Qianyi Hu, Xinhui Tu, Cong Guo, Shunping Zhang

NAACL 2025findings

Temporal knowledge graph question answering (TKGQA) addresses time-sensitive queries using knowledge bases. Although large language models (LLMs) and LLM-based agents such as ReAct have shown potential for TKGQA, they often lack sufficient temporal constraints in the retrieval process. To tackle thi…

Cited by 0 Source ↗PDF ↗Scholar ↗