Saved in:
Bibliographic Details
Main Authors: Mishra, Suyash, Li, Qiang, Girdhar, Anubhav
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.11957
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914325791244288
author Mishra, Suyash
Li, Qiang
Girdhar, Anubhav
author_facet Mishra, Suyash
Li, Qiang
Girdhar, Anubhav
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_11957
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Are Two LLMs Better Than One? A Student-Teacher Dual-Head LLMs Architecture for Pharmaceutical Content Optimization
Mishra, Suyash
Li, Qiang
Girdhar, Anubhav
Machine Learning
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.
title Are Two LLMs Better Than One? A Student-Teacher Dual-Head LLMs Architecture for Pharmaceutical Content Optimization
topic Machine Learning
url https://arxiv.org/abs/2602.11957