多智能体系统自动生成带可靠引用的查证文章
SourceMinds at CheckThat! 2026: NLI-Grounded Citation Auditing in a Multi-Agent Pipeline for Full Fact-Checking Article Generation
- 用多智能体流程整合检索、规划、生成与引用审核
- 通过自然语言推理检测缺失或冗余引用，提升可信度
- 适合需要高可信度内容生成的研究与媒体机构
本文介绍了我们在 CLEF 2026 CheckThat! 实验任务3中的系统，旨在从声明、真伪标签和证据文档自动生成完整的事实核查文章。提出一个包含多阶段的多智能体流水线：基于密集检索、重排序和源均衡选择的证据检索；结构化事实规划；生成带引用的文章；门控自我批判修正薄弱论证；以及基于自然语言推理（NLI）的引用审计，修复缺失引用并移除无支持或冗余引用。该方法强调了证据选择、结构化生成与生成后引用验证结合的重要性，对实现有源依据的事实核查文章生成具有关键意义。
原文摘要 · Abstract (English)
This paper presents our system for Task 3 of the CLEF 2026 CheckThat! Lab, which focuses on generating full fact-checking articles from claims, veracity labels, and evidence documents. We propose a multi-agent pipeline that combines evidence retrieval, structured fact planning, article generation, gated self-critique, and NLI-based citation auditing. The system retrieves claim-relevant evidence using dense retrieval, reranking, and source-balanced selection, then generates a citation-supported article from a structured plan. A gated self-critique stage revises weakly grounded drafts, while the NLI citation auditor repairs missing citations and removes unsupported or redundant ones. The approach highlights the importance of combining evidence selection, structured generation, and post-generation citation validation for source-grounded fact-checking article generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。