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

Spanish

Los datos de los grandes modelos de idiomas (LLM) se utilizan cada vez más para generar contenido comercial y médico específico de dominio (por ejemplo, reclamaciones, declaraciones y frases promocionales) en industrias reguladas como los productos farmacéuticos. Sin embargo, asegurar su cumplimiento regulatorio, exactitud de hechos y personalización específica de audiencia sigue siendo un gran reto. Informamos de un estudio de caso de producción preguntando si mover la conformidad y la personalización de los señales de referencia de las reglas de nivel prompt a un contexto de trabajo estructurado de recuperación mejora la generación de reclamaciones farmacéuticas, utilizando Composer, una herramienta interna implementada construida en un modelo de datos de oro (GDM) de 1,867 reclamaciones farmacéuticas que abarcan cuatro productos. El GDM integra metadatos de reclama

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