Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
3 results for “information extraction”
ConstructCIE: A Dataset for Extracting Causal Information from Construction Accident Narratives
Researchers released ConstructCIE, a manually annotated dataset for extracting hierarchical causal information from OSHA construction accident reports, revealing persistent gaps in LLM and sequence tagger performance on precise evidence-span extraction.
Aug 10, 2026
DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth
Researchers introduced DocOCR-Eval, an annotation-free framework to rank OCR and multimodal LLM tools for document parsing without ground-truth labels, addressing the challenge of tool selection in label-scarce real-world settings.
Jul 21, 2026
Behavioral Controllability of Agentic Models for Information Extraction: From Fixed Workflows to Reflective Agents
A new arXiv preprint investigates whether reflective LLM agents improve controllability and observable behavior over fixed workflows in scholarly dataset extraction, using process-level metrics rather than just accuracy.
Jul 20, 2026