用结构化推理压缩临床表单填充，提升准确率与稳定性。
LLM StructCore: Schema-Guided Reasoning Condensation and Deterministic Compilation
- 分两阶段处理：先生成9个关键域的结构化摘要，再用确定性编译器扩展为134项结果
- 在英文数据集上达到0.6543的宏平均F1，意大利语表现更优且无需语言定制
- 通过证据过滤和词汇规范化，有效避免虚假填报，适合医疗文本自动化场景
从临床笔记自动填充134项呼吸困难病例报告表（CRFs）面临语言噪声、输出约束严格及假阳性代价高等挑战。本文提出基于结构化推理（SGR）的两阶段方案：第一阶段生成仅含9个领域键的稳定JSON摘要；第二阶段为零大模型的确定性编译器，解析摘要、规范字段名、将预测映射至官方受控词表、应用证据门控的假阳性过滤，并展开为134项格式。在dev80划分上，最佳教师配置达英文宏平均F1 0.6543、意大利语0.6905；隐藏测试集（test200）上英文版本在Codabench得分为0.63。该流程语言无关，意大利语表现不逊于英文，无需额外语言工程。
原文摘要 · Abstract (English)
Automatically filling Case Report Forms (CRFs) from clinical notes is challenging due to noisy language, strict output contracts, and the high cost of false positives. We describe our CL4Health 2026 submission for Dyspnea CRF filling (134 items) using a contract-driven two-stage design grounded in Schema-Guided Reasoning (SGR). The key task property is extreme sparsity: the majority of fields are unknown, and official scoring penalizes both empty values and unsupported predictions. We shift from a single-step "LLM predicts 134 fields" approach to a decomposition where (i) Stage 1 produces a stable SGR-style JSON summary with exactly 9 domain keys, and (ii) Stage 2 is a fully deterministic, 0-LLM compiler that parses the Stage 1 summary, canonicalizes item names, normalizes predictions to the official controlled vocabulary, applies evidence-gated false-positive filters, and expands the output into the required 134-item format. On the dev80 split, the best teacher configuration achieves macro-F1 0.6543 (EN) and 0.6905 (IT); on the hidden test200, the submitted English variant scores 0.63 on Codabench. The pipeline is language-agnostic: Italian results match or exceed English with no language-specific engineering.
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。