Skip to content
conftrace_
2026 EACL EACL 2026

From Paper to Structured JSON: An Agentic AI Workflow for Compliant BMR Digital Transformation

Abstract

AbstractAgentic AI workflow converts noisy pharmaceutical batch records into validated JSON using hybrid OCR, vision–language and schema-guided LLMs, cutting QA review from hours to minutes while preserving GMP-critical structure.

Authors

Bhavik Agarwal, Nidhi Bendre, Viktoria Rojkova

Topics

Artificial Intelligence > Core AI > Multimodal Learning Machine Learning > Application Areas > Efficient Computing Deep Learning > Techniques > Model Architecture

Keywords

optical character recognition large language model schema validation intelligent document processing batch record good manufacturing practice
Download PDF

More from EACL 2026

All EACL 2026 papers →
From Sentences to Proof Trees: Leveraging Language Models for Structured Reasoning
Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration
SCRIPTMIND: Crime Script Inference and Cognitive Evaluation for LLM-based Social Engineering Scam Detection System
Compact Multimodal Language Models as Robust OCR Alternatives for Noisy Textual Clinical Reports
PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents
Evaluating the Pre-Consultation Ability of LLMs using Diagnostic Guidelines