Problem
Research questions and friction points this paper is trying to address.
Multi-Hop Knowledge Graph Question Answering
KGQA
reasoning steps
graph navigation
traceability
Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation
🤖 AI Summary
本文针对多跳知识图谱问答任务中推理路径不透明的问题，提出了一种将该任务视为图导航问题的新方法，并通过增强数据集、设计评估协议及改进现有模型来提高答案的可追溯性。
📝 Abstract
Multi-Hop Knowledge Graph Question Answering (KGQA) tasks require models to assemble relational evidence along paths in a KG to answer natural-language questions. However, existing KGQA systems typically focus on predicting the final answer without explicitly modeling or validating the intermediate reasoning steps, obscuring whether the correct answers arise from faithful multi-hop reasoning. To address this limitation, we re-frame multi-hop KGQA as a question-conditioned graph navigation problem. We refer to this formulation as THESEUS - Traceable Hop-wise Evidence SEarch in a Unified Semantics. In this setting, an agent receives a KG, a question, and a topic entity, and traverses a sequence of relations towards the answer, making the reasoning path explicit. To systematically study this formulation, we provide three key contributions. (i) We augment the existing KINSHIP and MQuAKE resources into navigation-ready KGQA datasets with annotated evidence paths and paraphrased questions. (ii) We design evaluation protocols to measure path fidelity, robustness to linguistic variation, and performance across multi-hop and multi-answer questions. (iii) We adapt established path-based KG completion agents - MINERVA, MultiHopKG, and SQUIRE - to operate on full question embeddings rather than symbolic single-relation queries, enabling their trajectories to be guided by natural-language semantics. Together, these contributions advance KGQA research toward systems where traceability is fundamental: answers are accompanied by explicit reasoning paths whose agreement with reference evidence can be systematically evaluated.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Traceable Hop-wise Evidence SEarch
question-conditioned graph navigation
path fidelity
natural-language semantics
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
