用AI分析全文验证引用准确性，防止误引和幻觉引用。
SemanticCite: Citation Verification with AI-Powered Full-Text Analysis and Evidence-Based Reasoning
- 通过多检索+四类分类判断引用是否支持、部分支持等关系。
- 轻量模型性能接近大模型，计算成本低，适合大规模验证。
- 开源数据集与工具链，适合科研诚信、审稿人和AI内容质检使用。
科学交流依赖准确的引用以验证来源并引导读者查找证据。然而学术文献面临语义引用错误、AI生成的虚构参考文献，以及传统引用仅指向整篇论文而无法定位具体支持段落等问题。我们提出SemanticCite，一个基于AI的全文引用验证系统，通过分析源文本提供详细推理过程与相关文字段落。该方法结合多种检索技术与四类分类体系（支持、部分支持、不支持、不确定），捕捉主张与来源间的细微关系，支持针对不同错误类型的修复操作。实验表明，微调后的轻量级语言模型在性能上可媲美大型商用系统，但计算开销显著降低，使大规模引用验证成为可能。系统提供透明、基于证据的解释，增强用户理解与信任。我们贡献了一个涵盖8个学科、超过1000条引用的综合性数据集，包含详细对齐、功能分类、语义标注及文献计量元数据，并开放了微调模型与完整验证框架。SemanticCite通过可扩展的引用验证机制，助力研究诚信、简化同行评审，强化AI生成内容的质量控制，为大规模维护引用准确性提供开源基础。
原文摘要 · Abstract (English)
Effective scientific communication depends on accurate citations that validate sources and guide readers to supporting evidence. Yet academic literature faces mounting challenges: semantic citation errors that misrepresent sources, AI-generated hallucinated references, and traditional citation formats that point to entire papers without indicating which sections substantiate specific claims. We introduce SemanticCite, an AI-powered system that verifies citation accuracy through full-text source analysis while providing rich contextual information via detailed reasoning and relevant text snippets. Our approach combines multiple retrieval methods with a four-class classification system (Supported, Partially Supported, Unsupported, Uncertain) that captures nuanced claim-source relationships and enables appropriate remedial actions for different error types. Our experiments show that fine-tuned lightweight language models achieve performance comparable to large commercial systems with significantly lower computational requirements, making large-scale citation verification practically feasible. The system provides transparent, evidence-based explanations that support user understanding and trust. We contribute a comprehensive dataset of over 1,000 citations with detailed alignments, functional classifications, semantic annotations, and bibliometric metadata across eight disciplines, alongside fine-tuned models and the complete verification framework as open-source software. SemanticCite addresses critical challenges in research integrity through scalable citation verification, streamlined peer review, and quality control for AI-generated content, providing an open-source foundation for maintaining citation accuracy at scale.
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。