LLM StructCore: Schema-Guided Reasoning Condensation and Deterministic Compilation
On the map: LLM reasoning → Clinical and biomedical applications
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 9 of its 15 references that are in the map. First posted on arXiv 22 Apr 2026.
Builds on
9 of 15 references.
References · 9
- 2022Large Language Models Encode Clinical Knowledgecited by 1,830
- 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,141
- 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
- 2019ScispaCy: Fast and Robust Models for Biomedical Natural Language Processingcited by 244
- 2024Capabilities of Gemini Models in Medicinecited by 237
- 2023Efficient Guided Generation for Large Language Modelscited by 200
- 2024XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Modelscited by 75
- 2025Converting Annotated Clinical Cases into Structured Case Report Formscited by 5
- 2026Small LLMs for Medical NLP: a Systematic Analysis of Few-Shot, Constraint Decoding, Fine-Tuning and Continual Pre-Training in Italiancited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Evaluating Hierarchical Clinical Document Classification Using Reasoning-Based LLMs
- 2025LLMSR@XLLM25: An Empirical Study of LLM for Structural Reasoning
- 2025Quantifying the Reasoning Abilities of LLMs on Real-world Clinical Cases
- 2026Closed-Loop Validation-Repair for Healthcare Interoperability: A Multi-Model Study of Schema Compliance in Clinical LLMs
- 2025MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports
- 2026KREL: Automatic Medical Coding via Knowledge-Guided Reasoning over Clinical Evidence with LLMs
- 2026When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation
- 2026Clinical Reasoning Graphs: Structured Evaluation of LLM Diagnostic Reasoning Reveals Competence Without Consistency