Can GPT-3 Pass a Writer’s Turing Test?

By Katherine Elkins, Jon Chun. 2020

187 citations recorded by the source corpus.

Until recently the field of natural language generation relied upon formalized grammar systems, small-scale statistical models, and lengthy sets of heuristic rules. This older technology was fairly limited and brittle: it could remix language into word salad poems or chat with humans within narrowly defined topics. Recently, very large-scale statistical language models have dramatically advanced the field, and GPT-3 is just one example. It can internalize the rules of language without explicit programming or rules. Instead, much like a human child, GPT-3 learns language through repeated exposure, albeit on a much larger scale. Without explicit rules, it can sometimes fail at the simplest of linguistic tasks, but it can also excel at more difficult ones like imitating an author or waxing philosophical.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Large Language Models, Natural Language Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yejin Choi
  2. Ronan Le Bras
  3. Maarten Sap
  4. Daniel Fried
  5. Noah A. Smith
  6. Alessandro Lenci
  7. Mohit Bansal
  8. Luke S. Zettlemoyer

In Computational Theory and Mathematics

  1. Alessandro Lenci
  2. Massimo Chiriatti
  3. Li Lucy
  4. Yejin Choi
  5. Luciano Floridi
  6. David Bamman
  7. Ronan Le Bras
  8. Daniel Fried

In Large Language Models

  1. Alessandro Lenci
  2. Yejin Choi
  3. Maarten Sap
  4. Li Lucy
  5. David Bamman
  6. Ronan Le Bras
  7. Daniel Fried
  8. Tuhin Chakrabarty

In Natural Language Generation

  1. Li Lucy
  2. Yejin Choi
  3. Alessandro Lenci
  4. David Bamman

Citations in the corpus