# LLM StructCore: Schema-Guided Reasoning Condensation and Deterministic Compilation

arXiv: https://arxiv.org/abs/2604.20560 · HTML: https://mlsanity.com/paper/2604.20560/

## 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.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 9 of 9)

- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing](https://mlsanity.com/paper/1902.07669/) (2019)
- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models](https://mlsanity.com/paper/2411.15100/) (2024)
- [Converting Annotated Clinical Cases into Structured Case Report Forms](https://mlsanity.com/paper/2506.11666/) (2025)
- [Small LLMs for Medical NLP: a Systematic Analysis of Few-Shot, Constraint Decoding, Fine-Tuning and Continual Pre-Training in Italian](https://mlsanity.com/paper/2602.17475/) (2026)

## 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.