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

Andrew Bouras
7/4/2024
cs.CLcs.AI

No official code found. Best implementation: andrewbouras/randomnesspaper (0 stars, MIT, last commit 2024-07-04).

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.

View on arXivView PDF

Code Implementations(1)

andrewbouras/randomnesspaperCommunity100%
MIT
00PythonJul 3, 20242 years agoMIT

Similar Papers

A Comparison of Large Language Model and Human Performance on Random Number Generation Tasks

81% match1 repo2024

Leveraging Generative AI to Enhance Synthea Module Development

81% match2025

Deterministic or probabilistic? The psychology of LLMs as random number generators

81% match2025

Addressing LLM Diversity by Infusing Random Concepts

80% match2026

Scientific Hypothesis Generation by a Large Language Model: Laboratory Validation in Breast Cancer Treatment

80% match2024

Evaluating n-Gram Novelty of Language Models Using Rusty-DAWG

80% match1 repo312024

Cite this paper

@article{bouras2024integrating,
  title  = {Integrating Randomness in Large Language Models: A Linear Congruential Generator Approach for Generating Clinically Relevant Content},
  author = {Andrew Bouras},
  year   = {2024},
  eprint = {2407.03582},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.03582v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.03582.svg)](https://codeofpaper.com/paper/2407.03582)

Discussion