Sept. 27, 2023, 4:35 a.m. | Dhruv Matani

Towards Data Science - Medium towardsdatascience.com

We’ll take an in-depth look at the challenges of detecting AI-generated text, and the effectiveness of the techniques used in practice.

Photo by Houcine Ncib on Unsplash

Co-authored with Naresh Singh.

Table of contents

  1. Introduction
  2. Building an intuition for text source detection
  3. What is the perplexity of a language model?
  4. Computing the perplexity of a language model’s prediction
  5. Detecting AI-generated text
  6. Misinformation
  7. What’s next?
  8. Conclusion

Introduction

AI-assisted technologies for writing articles or posts are everywhere now! ChatGPT has unlocked …

ai-generated text challenges computing generated getting-started gptzero intuition language language model llm look next perplexity photo practice singh table technologies text

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne