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

arXiv: https://arxiv.org/abs/2602.11957 · HTML: https://mlsanity.com/paper/2602.11957/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification](https://mlsanity.com/paper/2506.15569/) (2025)
- [The Confidence Paradox: Can LLM Know When It's Wrong](https://mlsanity.com/paper/2506.23464/) (2025)
- [PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines](https://mlsanity.com/paper/2504.14738/) (2025)
- [Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions](https://mlsanity.com/paper/2411.09018/) (2024)
- [XIMAGENET-12: An Explainable AI Benchmark Dataset for Model Robustness Evaluation](https://mlsanity.com/paper/2310.08182/) (2023)
- [Scaling Vision Language Models for Pharmaceutical Long Form Video Reasoning on Industrial GenAI Platform](https://mlsanity.com/paper/2601.04891/) (2026)
- [From Understanding to Engagement: Personalized pharmacy Video Clips via Vision Language Models (VLMs)](https://mlsanity.com/paper/2601.05059/) (2026)

## Abstract (arXiv)

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.