用大模型自动审查德国央行证券准入资格，准确率超91%。
LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank
- 分三步提取、归一化、解释信息，适应混杂语言和噪声文本。
- 在文档级判断中达到91%精确率，避免误接受风险。
- 首次用大模型评估合规性，适合金融监管与合规科技场景。
德国中央银行需验证证券是否符合抵押品资格，但手动审核长篇半结构化、常含德英双语的招股说明书极为耗时。以往基于传统命名实体识别（NER）的方法难以应对光学字符识别噪声、语言差异及固定片段约束，且需为每类标注手动标注训练数据。本文首次将大语言模型（LLM）应用于该审查流程，转向生成式信息抽取范式。方法分为提取、归一化与解释三阶段，提升对噪声文本和跨语言内容的处理灵活性。引入基于大模型的评价机制（LLM-as-a-judge），实现更语义化的评估，超越传统位置匹配指标。结果表明，基于大模型的系统在文档级资格判断中精确率达91%，表现出保守策略，有效降低误接受风险。
原文摘要 · Abstract (English)
Verifying the eligibility of securities as collateral is a key responsibility of the German Central Bank. However, manually verifying these assets against legal and financial criteria within lengthy, semi-structured, and often bilingual prospectuses is a resource-intensive task. While previous efforts utilized traditional Named Entity Recognition (NER) for information extraction, these methods can struggle with OCR noise, linguistic variance, and rigid span-based constraints, and the need for manually annotated training data for each relevant annotation type. In this paper, we present the first case study applying Large Language Models (LLMs) to the eligibility examination process, shifting the paradigm toward a generative Information Extraction pipeline. Our approach decomposes the task into extraction, normalization, and interpretation, allowing for greater flexibility in handling noisy text and interleaved German-English content. We further introduce a value-based evaluation methodology using LLM-as-a-judge, which offers a more semantic assessment than location-based metrics. Our results demonstrate that LLM-based systems achieve high precision (up to 91%) in document-level eligibility, exhibiting a conservative operating profile that minimizes false acceptance.
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。