用大模型+逻辑网络验证政府采购文件，决策可解释且合规。
From Large Language Model Predicates to Logic Tensor Networks: Neurosymbolic Offer Validation in Regulated Procurement
- 大模型提取文本信息，逻辑张量网络整合知识做判断
- 在真实数据集上性能媲美现有模型，但可解释性更强
- 适合需要审计和合规的政府、金融等高监管场景
我们提出一种神经符号方法，用于在受监管的公共机构中验证投标文件。该方法利用语言模型提取信息，并通过逻辑张量网络（LTN）进行聚合，生成可审计的决策。在受监管的公共机构中，决策必须既事实正确又法律可追溯。本方法将领域专有知识与语言模型的语义理解相结合，决策结果可通过谓词值、规则真值及对应文本片段进行解释。在真实语料库上的实验表明，所提流程性能与现有模型相当，其核心优势在于可解释性、模块化谓词提取以及对可解释人工智能（XAI）的显式支持。
原文摘要 · Abstract (English)
We present a neurosymbolic approach, i.e. combine symbolic and subsymbolic artificial intelligence, to validating offer documents in regulated public institutions. We employ a language model to extract information and then aggregate it with an LTN (Logic Tensor Network) to make an auditable decision. In regulated public institutions, decisions must be made in a manner that is both factually correct and legally verifiable. Our neurosymbolic approach allows existing domain-specific knowledge to be linked to the semantic text understanding of language models. The decisions resulting from our pipeline can be justified by predicate values, rule truth values, and corresponding text passages. Our experiments on a real corpus show that the proposed pipeline achieves performance comparable to existing models, but its key advantage lies in its interpretability, modular predicate extraction, and explicit support for XAI (Explainable AI).
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。