4 papers
Can You Trust the Confidence? ConfBench for Vision-Language Models on Document Extraction
Priyashree Roy, Sujitha Martin, Mohammad Rostami +6
Intelligent document processing (IDP) with vision-language models (VLMs) hinges on confidence scores trustworthy enough to route extractions between automation and human review. Ex…
Brick-DICL: Dynamic In-Context Learning for Automated Brick Schema Classification
Yiyue Qian, Shinan Zhang, Huan Song +3
Building Management Systems (BMS) are essential for optimizing energy efficiency and operational performance in modern buildings. However, the lack of standardization across BMS po…
IDP Accelerator: Agentic Document Intelligence from Extraction to Compliance Validation
Md Mofijul Islam, Md Sirajus Salekin, Joe King +8
Understanding and extracting structured insights from unstructured documents remains a foundational challenge in industrial NLP. While Large Language Models (LLMs) enable zero-shot…
CollabEval: Enhancing LLM-as-a-Judge via Multi-Agent Collaboration
Yiyue Qian, Shinan Zhang, Yun Zhou +3
Large Language Models (LLMs) have revolutionized AI-generated content evaluation, with the LLM-as-a-Judge paradigm becoming increasingly popular. However, current single-LLM evalua…