Tag
该论文提出一种知识引导的LLM框架，结合语法约束语义解析与知识图谱驱动的澄清循环，用于集成地面与非地面6G网络中的意图驱动服务编排，在200条意图数据集上达到89%分类准确率与95%策略有效性。
该论文首次在黑盒设定下研究 AMR 解析器输出的不确定性估计，利用 top-k beam-search 候选间的成对相似度评估可靠性，并通过 Prediction Rejection Ratio 分析解析性能与不确定性的关系，识别出性能与可靠性平衡最佳的解析器。
Weave is a Git extension that performs entity-level semantic merging to resolve conflicts by parsing code into functions, classes, and keys using tree-sitter, especially useful for AI-driven development.
This paper proposes a symbolic framework that converts redacted police narratives into evidence-linked facts using ontology, semantic parsing (AMR), and reasoning, enabling structured querying of incident details that are typically only available in free text.