让下一篇重要论文，不再错过。

原文摘要

Large language models (LLMs) are increasingly used for knowledge base question answering (KBQA), also referred to as knowledge graph question answering (KGQA), where answering requires selecting entities from a question-specific knowledge graph subgraph. Yet LLMs are known to hallucinate across tasks, and KBQA is no exception: even when we provide a graph as the knowledge source, the model may rely on parametric knowledge instead of graph evidence or perform invalid reasoning over the given relations. Such hallucinated answer nodes can limit the practical deployment of KBQA systems, especially in high-stakes domains such as healthcare. We formulate hallucination detection in KBQA as an answer-node classification problem and propose a lightweight graph-based framework that treats the answering LLM as a black box. KG-Guard represents each KBQA instance as an augmented graph. It initializes node features with semantic representations of KG entities, marks topic entities and LLM-proposed answer nodes with learned vectors, and connects a virtual question node to the topic entities. A graph encoder then produces verification-oriented node representations, and a small MLP classifies each proposed answer node using its graph representation together with the question embedding. Experiments on WebQSP, ComplexWebQuestions, and PUGG show that our detector achieves the best average rank across all three benchmarks (F1 82.0, 87.4, and 84.3), while using ${\sim}$305$\times$ fewer parameters than LLM-based baselines. It also retains the best average rank when jointly evaluated across an extended set of pipelines and settings. Beyond detection, the node-level feedback is actionable: when flagged answers are fed back to the KBQA system for iterative refinement, downstream KBQA F1 improves by 13.0-14.5 points and Exact Match by 16.9-17.6 points.