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

Indonesian

Data model bahasa besar (LLM) data semakin digunakan untuk menghasilkan konten komersial dan medis spesifik domain (misalnya klaim, pernyataan, dan frasa promosi) dalam industri yang diatur seperti farmasi. Namun, memastikan kepatuhan peraturan, akurasi fakta, dan personalisasi spesifik audiens tetap menjadi tantangan utama. Kami melaporkan studi kasus produksi yang menanyakan apakah memindahkan kepatuhan dan sinyal personalisasi dari aturan tingkat prompt ke dalam konteks kerja terstruktur waktu pencarian meningkatkan generasi klaim farmasi, menggunakan Composer, alat internal yang didistribusikan yang dibangun pada Model Data Emas (GDM) dari 1,867 klaim farmasi yang mencakup empat produk. GDM mengintegrasikan metadata klaim, bukti referensi, label audiens, jenis bahan, riwayat penggunaan, tautan Variant Text Match (MTV) kerja, dan skor kualitas enam dimensi

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