Integrating Randomness in Large Language Models: A Linear Congruential Generator Approach for Generating Clinically Relevant Content

TL;DR

This paper introduces a novel approach using Linear Congruential Generator to enhance randomness and diversity in GPT-4o generated clinical content, addressing repetition and quality issues.

Contribution

It presents a systematic method combining LCG with AI to produce diverse, clinically relevant outputs, improving content variety and quality in language models.

Findings

98 unique outputs over 14 rounds

Effective reduction of repetition and increased diversity

Enhanced clinical relevance of generated content

Abstract

Generating diverse, high-quality outputs from language models is crucial for applications in education and content creation. Achieving true randomness and avoiding repetition remains a significant challenge. This study uses the Linear Congruential Generator method for systematic fact selection, combined with AI-powered content generation. We ensured unique combinations of gastrointestinal physiology and pathology facts across multiple rounds, integrating these facts into prompts for GPT-4o to create clinically relevant, vignette-style outputs. Over 14 rounds, 98 unique outputs were generated, demonstrating LCG's effectiveness in producing diverse and high-quality content. This method addresses key issues of randomness and repetition, enhancing the quality and efficiency of language model-generated content for various applications.