# The COVID That Wasn't: Counterfactual Journalism Using GPT

arXiv: https://arxiv.org/abs/2210.06644 · HTML: https://mlsanity.com/paper/2210.06644/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 42 references that are in the map.
- First posted on arXiv 13 Oct 2022.

## Builds on (most cited first, 4 of 4)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Systematic Evaluation of Large Language Models of Code](https://mlsanity.com/paper/2202.13169/) (2022)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [Pandemic Populism: Facebook Pages of Alternative News Media and the Corona Crisis -- A Computational Content Analysis](https://mlsanity.com/paper/2004.02566/) (2020)

## Built on by (most cited first, 4 of 4)

- [Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4](https://mlsanity.com/paper/2305.00118/) (2023)
- [Blind Judgement: Agent-Based Supreme Court Modelling With GPT](https://mlsanity.com/paper/2301.05327/) (2023)
- [Estimating Causal Effects of Text Interventions Leveraging LLMs](https://mlsanity.com/paper/2410.21474/) (2024)
- [Enhancing Journalism with AI: A Study of Contextualized Image Captioning for News Articles using LLMs and LMMs](https://mlsanity.com/paper/2408.04331/) (2024)

## Abstract (arXiv)

In this paper, we explore the use of large language models to assess human interpretations of real world events. To do so, we use a language model trained prior to 2020 to artificially generate news articles concerning COVID-19 given the headlines of actual articles written during the pandemic. We then compare stylistic qualities of our artificially generated corpus with a news corpus, in this case 5,082 articles produced by CBC News between January 23 and May 5, 2020. We find our artificially generated articles exhibits a considerably more negative attitude towards COVID and a significantly lower reliance on geopolitical framing. Our methods and results hold importance for researchers seeking to simulate large scale cultural processes via recent breakthroughs in text generation.