# Adapt Semantics, Not Structure: Few-Instance Schema Calibration for Scientific PDF Extraction

arXiv: https://arxiv.org/abs/2609.34841 · HTML: https://mlsanity.com/paper/2609.34841/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [SciREX: A Challenge Dataset for Document-Level Information Extraction](https://mlsanity.com/paper/2005.00512/) (2020)
- [Document-level Entity-based Extraction as Template Generation](https://mlsanity.com/paper/2109.04901/) (2021)
- [A general-purpose material property data extraction pipeline from large polymer corpora using Natural Language Processing](https://mlsanity.com/paper/2209.13136/) (2022)
- [Mining experimental data from Materials Science literature with Large Language Models: an evaluation study](https://mlsanity.com/paper/2401.11052/) (2024)
- [Reconstructing Materials Tetrahedron: Challenges in Materials Information Extraction](https://mlsanity.com/paper/2310.08383/) (2023)
- [Learning to Extract Structured Entities Using Language Models](https://mlsanity.com/paper/2402.04437/) (2024)
- [PARSE: LLM Driven Schema Optimization for Reliable Entity Extraction](https://mlsanity.com/paper/2510.08623/) (2025)
- [Your Prompt Is Not the Only Prompt: How Much Do LLMs Weight Structured-Output Schema Descriptions?](https://mlsanity.com/paper/2608.08254/) (2026)

## Abstract (arXiv)

A well-designed extraction schema is not necessarily ready for reliable LLM execution. When only limited verified extractions are available, manually tuning hundreds of field definitions through trial and error is costly. We frame this problem as few-instance schema calibration: adapting the operational semantics of an existing schema from a few annotated documents while preserving its structural contract. We introduce CPSE, a contract-preserving semantic extraction framework that jointly calibrates extraction prompts and field-level semantic descriptions from a few gold annotations. CPSE decomposes the schema into an invariant structural contract and mutable field semantics, and further separates identity discovery from record completion using manifest-conditioned resolution. On expert-annotated polymer-science documents, CPSE improves extraction by 9.93 points over an execution-matched baseline, with consistent gains under an independent judge and in a blinded expert audit. These results show that CPSE enables low-resource schema execution while preserving the output structure required downstream.