用图结构分析论文逻辑，自动评估可信度。
Plato's Cave: A Human-Centered Research Verification System
- 构建论文的有向无环图，追踪论证链条
- 通过网络代理给每个节点和边打可信分
- 适合科研人员验证论文可靠性
研究论文发表速度加快，亟需更有效的信息核查、写作质量评估和不可验证主张识别方法。我们提出 Plato's Cave，一个开源的以人类为中心的研究验证系统，该系统（i）从文档中构建有向无环图（DAG），（ii）利用网络代理为 DAG 中的节点和边分配可信度评分，（iii）通过解析和评估论文的论证结构给出最终评分。我们在收集的104篇研究论文数据集上报告了系统实现与结果。
原文摘要 · Abstract (English)
The growing publication rate of research papers has created an urgent need for better ways to fact-check information, assess writing quality, and identify unverifiable claims. We present Plato's Cave as an open-source, human-centered research verification system that (i) creates a directed acyclic graph (DAG) from a document, (ii) leverages web agents to assign credibility scores to nodes and edges from the DAG, and (iii) gives a final score by interpreting and evaluating the paper's argumentative structure. We report the system implementation and results on a collected dataset of 104 research papers.
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。