ClaimPKG：通过轻量级专用LLM生成伪子图增强声明验证
ClaimPKG: Enhancing Claim Verification via Pseudo-Subgraph Generation with Lightweight Specialized LLM
AI总结：
提出ClaimPKG框架，通过轻量级专用LLM生成伪子图引导KG子图检索，结合通用LLM生成裁决，在FactKG上实现SOTA并具备零样本泛化能力。
摘要：
将知识图谱（KGs）集成以增强大型语言模型（LLMs）的推理能力，是声明验证中一个新兴的研究挑战。尽管KGs提供了结构化、语义丰富的表示，非常适合推理，但大多数现有的验证方法依赖于非结构化文本语料库，限制了它们有效利用KGs的能力。此外，尽管现代LLMs具备强大的推理能力，但在未经适配的情况下，它们在处理多步模块化管道和对KGs进行推理时仍面临困难。为了应对这些挑战，我们提出了ClaimPKG，这是一个端到端框架，将LLM推理与来自KGs的结构化知识无缝集成。具体而言，ClaimPKG的主要思想是采用一个轻量级、专用LLM将输入声明表示为伪子图，引导专用子图检索模块识别相关的KG子图。这些检索到的子图随后由通用LLM处理，以产生最终裁决和理由。在FactKG数据集上的大量实验表明，ClaimPKG实现了最先进的性能，在多个类别中以9%-12%的准确率优势超越了该研究领域的强基线。此外，ClaimPKG对HoVer和FEVEROUS等非结构化数据集展现出零样本泛化能力，有效地将来自KGs的结构化知识与各种LLM骨干中的LLM推理相结合。
英文摘要：
Integrating knowledge graphs (KGs) to enhance the reasoning capabilities of large language models (LLMs) is an emerging research challenge in claim verification. While KGs provide structured, semantically rich representations well-suited for reasoning, most existing verification methods rely on unstructured text corpora, limiting their ability to effectively leverage KGs. Additionally, despite possessing strong reasoning abilities, modern LLMs struggle with multi-step modular pipelines and reasoning over KGs without adaptation. To address these challenges, we propose ClaimPKG, an end-to-end framework that seamlessly integrates LLM reasoning with structured knowledge from KGs. Specifically, the main idea of ClaimPKG is to employ a lightweight, specialized LLM to represent the input claim as pseudo-subgraphs, guiding a dedicated subgraph retrieval module to identify relevant KG subgraphs. These retrieved subgraphs are then processed by a general-purpose LLM to produce the final verdict and justification. Extensive experiments on the FactKG dataset demonstrate that ClaimPKG achieves state-of-the-art performance, outperforming strong baselines in this research field by 9%-12% accuracy points across multiple categories. Furthermore, ClaimPKG exhibits zero-shot generalizability to unstructured datasets such as HoVer and FEVEROUS, effectively combining structured knowledge from KGs with LLM reasoning across various LLM backbones.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
