用大模型自动验证技术声明真伪，无需专业背景
AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models
- 将技术陈述拆解为三元组，构建分层知识图谱进行推理
- 在量子计算争议声明中发现夸大表述与数据矛盾
- 适合科技情报分析人员快速评估新兴技术可信度
科学与技术情报分析需验证快速增长文献中的复杂技术声明，现有方法难以跨越表层准确性与深层方法有效性之间的验证鸿沟。我们提出AutoVerifier，一个基于大语言模型的代理式自动化验证框架，可在无需领域专业知识的情况下实现技术声明的端到端验证。该框架将每项技术断言分解为（主体，谓词，客体）结构化三元组，构建分层知识图谱，支持六层逐步增强的推理：语料构建与导入、实体与断言抽取、文档内验证、跨源验证、外部信号佐证及最终假设矩阵生成。我们在一个存在争议的量子计算声明上验证了AutoVerifier，由无量子背景的分析师操作，系统自动识别出目标论文中的过度宣称和度量不一致，追溯跨源矛盾，发现未披露的商业利益冲突，并生成最终评估报告。结果表明，结构化LLM验证可可靠评估新兴技术的有效性与成熟度，将原始技术文档转化为可追溯、有证据支持的情报评估。
原文摘要 · Abstract (English)
Scientific and Technical Intelligence (S&TI) analysis requires verifying complex technical claims across rapidly growing literature, where existing approaches fail to bridge the verification gap between surface-level accuracy and deeper methodological validity. We present AutoVerifier, an LLM-based agentic framework that automates end-to-end verification of technical claims without requiring domain expertise. AutoVerifier decomposes every technical assertion into structured claim triples of the form (Subject, Predicate, Object), constructing knowledge graphs that enable structured reasoning across six progressively enriching layers: corpus construction and ingestion, entity and claim extraction, intra-document verification, cross-source verification, external signal corroboration, and final hypothesis matrix generation. We demonstrate AutoVerifier on a contested quantum computing claim, where the framework, operated by analysts with no quantum expertise, automatically identified overclaims and metric inconsistencies within the target paper, traced cross-source contradictions, uncovered undisclosed commercial conflicts of interest, and produced a final assessment. These results show that structured LLM verification can reliably evaluate the validity and maturity of emerging technologies, turning raw technical documents into traceable, evidence-backed intelligence assessments.
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。