Newest papers

From Prompt Rules to Golden Data Model: Production-Scale Generation of Personalized, Compliant Pharmaceutical Claims

Suyash Mishra, Qiang Li, Subhabrata Adak, Upender Phogat, Srikanth Patil, Satyanarayan Pati · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31519 · cited by 0 works (OpenAlex) · open-access PDF

French

Les données de grands modèles de langues (LLM) sont de plus en plus utilisées pour générer des contenus commerciaux et médicaux spécifiques au domaine (par exemple, revendications, déclarations et phrases promotionnelles) dans des industries réglementées telles que les produits pharmaceutiques. Cependant, assurer sa conformité réglementaire, sa précision factuelle et sa personnalisation spécifique au public reste un défi majeur. Nous rapportons une étude de cas de production demandant si le déplacement de la conformité et du signal de personnalisation des règles de niveau prompt dans un contexte de travail structuré améliore la génération de revendications pharmaceutiques, en utilisant Composer, un outil interne déployé construit sur un modèle de données d'or (GDM) de 1,8

Machine translation (Meta M2M100); the English original follows.

Abstract

Large language models (LLMs) are increasingly used to generate domain-specific commercial & medical content (e.g., claims, statements, and promotional phrases) in regulated industries such as pharmaceuticals. However, ensuring its regulatory compliance, factual accuracy, and audience-specific personalization remains a major challenge. We report a production case study asking whether moving compliance and personalization signal from prompt-level rules into retrieval time structured context improves pharmaceutical claims generation, using Composer, a deployed internal tool built on a Golden Data Model (GDM) of 1,867 pharmaceutical claims spanning four products. The GDM integrates claim metadata, references, audience labels, material type, usage history, Match Text Variant (MTV) links, and a six dimension quality score (6C). Across six product-audience segments, the context pipeline improves intended indication (+29%), intended content type (+62%) and intended target audience (+67%), 6C quality score (+86%), and claim reuse (+34%). Production log analysis over the deployment period shows a 29.5% reduction in weekly API cost. We report this as descriptive deployment evidence. This work is a systems and data architecture contribution: it shows that in a regulated, high-stakes domain, restructuring claim data for retrieval-time filtering is a more scalable lever than expanding prompt-level rules, and documents the engineering path data cleaning, graph linking, and quality scoring.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Personalization, Computer science, Software deployment, Context (archaeology), Pipeline (software), Quality (philosophy)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange