Evaluating Structured Output Robustness of Small Language Models for Open Attribute-Value Extraction from Clinical Notes

Nikita Neveditsin, Pawan Lingras, Vijay Kumar Mago

Keywords: Open information extraction, clinical notes, structured output, small language models

TL;DR: short paper, archival track

Abstract: We present a comparative analysis of the parseability of structured outputs generated by small language models for open attribute-value extraction from clinical notes. We evaluate three widely used serialization formats: JSON, YAML, and XML, and find that JSON consistently yields the highest parseability. Structural robustness improves with targeted prompting and larger models, but declines for longer documents and certain note types. Our error analysis identifies recurring format-specific failure patterns. These findings offer practical guidance for selecting serialization formats and designing prompts when deploying language models in privacy-sensitive clinical settings.

Archival Status: Archival

Paper Length: Short Paper (up to 4 pages of content)

Submission Number: 65