MedStruct-S benchmark shows encoder-only models outperform larger decoder-only ones on key-conditioned QA from noisy OCR clinical reports, with fine-tuned large models winning only when scale is ignored.
Information Extraction from Visually Rich Documents using LLM -based Organization of Documents into Independent Textual Segments
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Decomposing annotation tasks using centers from centering theory reduces aggregate inferential load via a degrees-of-freedom model and enables better sub-task allocation.
citing papers explorer
-
MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
MedStruct-S benchmark shows encoder-only models outperform larger decoder-only ones on key-conditioned QA from noisy OCR clinical reports, with fine-tuned large models winning only when scale is ignored.
-
Task Decomposition for Efficient Annotation
Decomposing annotation tasks using centers from centering theory reduces aggregate inferential load via a degrees-of-freedom model and enables better sub-task allocation.