KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering

• URL: http://arxiv.org/abs/2606.00328v1
• Date: Fri, 29 May 2026 20:11:41 GMT
• Title: KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering
• Abstract summary: Large language models (LLMs) are increasingly used for knowledge base question answering (KBQA)<n>LLMs are known to hallucinate across tasks, and KBQA is no exception.<n>We formulate detection in KBQA as an answer-node classification problem and propose a lightweight graph-based framework.
• Score: 3.765096298134585
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models (LLMs) are increasingly used for knowledge base question answering (KBQA), 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. \methodname 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 connect 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 highest F1 on all three benchmarks ($82.0$, $87.4$, and $84.3$), outperforming LLM-as-judge and sampling-based baselines, while having $\sim305\times$ fewer parameters than the reference approaches. 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.

Related papers

• Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting [11.222318740825388]
  Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios.<n>In this paper, we propose a novel graph-based soft prompting framework that shifts the reasoning paradigm to subgraph-level reasoning.<n> Experiments on four multi-hop KBQA benchmarks show that our approach achieves state-of-the-art performance on three of them, demonstrating its effectiveness.
  arXiv  Detail & Related papers  (2026-04-14T09:27:52Z)
• Multi-hop Question Answering over Knowledge Graphs using Large Language Models [1.8130068086063336]
  We evaluate the capability of (LLMs) to answer questions over Knowledge graphs that involve multiple hops. We show that depending upon the size and nature of the KG we need different approaches to extract and feed the relevant information to an LLM.
  arXiv  Detail & Related papers  (2024-04-30T03:31:03Z)
• PipeNet: Question Answering with Semantic Pruning over Knowledge Graphs [56.5262495514563]
  We propose a grounding-pruning-reasoning pipeline to prune noisy computation nodes. We also propose a graph attention network (GAT) based module to reason with the subgraph data.
  arXiv  Detail & Related papers  (2024-01-31T01:37:33Z)
• ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph [142.42275983201978]
  We propose a subgraph-aware self-attention mechanism to imitate the GNN for performing structured reasoning. We also adopt an adaptation tuning strategy to adapt the model parameters with 20,000 subgraphs with synthesized questions. Experiments show that ReasoningLM surpasses state-of-the-art models by a large margin, even with fewer updated parameters and less training data.
  arXiv  Detail & Related papers  (2023-12-30T07:18:54Z)
• Open-Set Knowledge-Based Visual Question Answering with Inference Paths [79.55742631375063]
  The purpose of Knowledge-Based Visual Question Answering (KB-VQA) is to provide a correct answer to the question with the aid of external knowledge bases. We propose a new retriever-ranker paradigm of KB-VQA, Graph pATH rankER (GATHER for brevity) Specifically, it contains graph constructing, pruning, and path-level ranking, which not only retrieves accurate answers but also provides inference paths that explain the reasoning process.
  arXiv  Detail & Related papers  (2023-10-12T09:12:50Z)
• Logical Message Passing Networks with One-hop Inference on Atomic Formulas [57.47174363091452]
  We propose a framework for complex query answering that decomposes the Knowledge Graph embeddings from neural set operators. On top of the query graph, we propose the Logical Message Passing Neural Network (LMPNN) that connects the local one-hop inferences on atomic formulas to the global logical reasoning. Our approach yields the new state-of-the-art neural CQA model.
  arXiv  Detail & Related papers  (2023-01-21T02:34:06Z)
• Knowledge Base Question Answering by Case-based Reasoning over Subgraphs [81.22050011503933]
  We show that our model answers queries requiring complex reasoning patterns more effectively than existing KG completion algorithms. The proposed model outperforms or performs competitively with state-of-the-art models on several KBQA benchmarks.
  arXiv  Detail & Related papers  (2022-02-22T01:34:35Z)
• Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph [34.774049199809426]
  Knowledge graph question answering (i.e., KGQA) based on information retrieval aims to answer a question by retrieving answer from a large-scale knowledge graph. We first propose to partition the retrieved KSG to several smaller sub-KSGs via a new subgraph partition algorithm. We then present a graph-augmented learning to rank model to select the top-ranked sub-KSGs from them.
  arXiv  Detail & Related papers  (2021-11-20T08:27:37Z)
• Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks [53.58077686470096]
  Knowledge graph (KG) question generation (QG) aims to generate natural language questions from KGs and target answers. In this work, we focus on a more realistic setting where we aim to generate questions from a KG subgraph and target answers.
  arXiv  Detail & Related papers  (2020-04-13T15:43:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.