Are Two LLMs Better Than One? A Student-Teacher Dual-Head LLMs Architecture for Pharmaceutical Content Optimization

TL;DR

This paper presents LRBTC, a dual-model architecture combining language and vision models with human oversight to improve quality control of pharmaceutical content, achieving high accuracy and reducing violations.

Contribution

It introduces a novel Student-Teacher dual model framework with waterfall rule filtering for scalable, verifiable content validation in regulated industries.

Findings

Achieves 83.0% F1 and 97.5% recall on AIReg-Bench.

Reduces missed violations by 5x compared to Gemini 2.5 Pro.

Improves mean accuracy by 26.7% on CSpelling.

Abstract

Large language models (LLMs) are increasingly used to create content in regulated domains such as pharmaceuticals, where outputs must be scientifically accurate and legally compliant. Manual quality control (QC) is slow, error prone, and can become a publication bottleneck. We introduce LRBTC, a modular LLM and vision language model (VLM) driven QC architecture covering Language, Regulatory, Brand, Technical, and Content Structure checks. LRBTC combines a Student-Teacher dual model architecture, human in the loop (HITL) workflow with waterfall rule filtering to enable scalable, verifiable content validation and optimization. On AIReg-Bench, our approach achieves 83.0% F1 and 97.5% recall, reducing missed violations by 5x compared with Gemini 2.5 Pro. On CSpelling, it improves mean accuracy by 26.7%. Error analysis further reveals that while current models are strong at detecting misspellings (92.5 recall), they fail to identify complex medical grammatical (25.0 recall) and punctuation (41.7 recall) errors, highlighting a key area for future work. This work provides a practical, plug and play solution for reliable, transparent quality control of content in high stakes, compliance critical industries. We also provide access to our Demo under MIT Licenses.