ChatGPT's Work Lacks Transparency and That Is a Problem


May 8, 2023

ChatGPT logo in an illustration from March 31, 2023 ,photo by Dado Ruvic/Reuters, photo by Dado Ruvic/Reuters

ChatGPT logo in this illustration from March 31, 2023

Photo by Dado Ruvic/Reuters

After getting a set of questions about the COVID-19 pandemic and putting together my responses, I thought that I would see how ChatGPT would do.

While ChatGPT could not provide concrete data or citations to back up its point, even with more prompting, and it missed some nuance, this is a nice first start for a summary of the consensus view on the key takeaways from the pandemic—and that is the problem.

At their core, ChatGPT and other Large Language Models (LLMs) estimate the most likely next word, phrase, or sentence to follow a prompt from a user. To make these estimates, LLMs are trained on millions or even billions of texts that include recent news stories, articles, and other work. When asked about lessons learned from the COVID-19 pandemic, ChatGPT pulls from this vast corpus to predict the most likely set of sentences to respond.

To that end, the response can be seen as an amalgamation of the training pool of writing on COVID-19, text on lessons learned, and the general rules of language from the full corpus. This works well, but when prompted for more details about the specifics of the points presented, a LLM may not have the appropriate details in its corpus and can't necessarily predict the best information to provide. This can make the content of the responses to followup questions underwhelming or even false (when asked for sources, ChatGPT produced three references that appear to be fictitious).

The first point regarding public health infrastructure is not necessarily inaccurate but is by no means obvious or a settled question. Many of the poorest countries with relatively weak health infrastructure fared quite well due in large part to their populations being much younger than those in wealthier nations.

Comparing only rich nations, there was substantial variation in COVID-19 outcomes and health spending. While public health infrastructure was important in the COVID-19 response, this is not a clear takeaway from international comparisons as stated (there may be a stronger case within the United States). The other points made by ChatGPT are stronger but not without their shortcomings.

Developers need to be more transparent about their algorithms and data sources so that people can assess the inherent sources of bias or problems with the approach.

Share on Twitter

With these content critiques in mind, ChatGPT's five points provide a useful start for a summary of key takeaways. However, the fact that it is coherently written and, on first glance, very reasonable, is quite problematic because of the lack of transparency.

When someone reads a research study or a newspaper article, facts are typically sourced, and those sources have (hopefully) been verified. While there have been high-profile cases of a few journalists making up facts, the fact that this occurrence is so rare is what makes these cases high profile. This is not true for LLMs at present.

In a world with LLMs, there is a growing need for modernized data literacy. While basic numeracy is useful when reading statistical analysis, that is not sufficient to understanding how to treat outputs from LLMs and other modern AI. Developers need to be more transparent about their algorithms and data sources so that people can assess the inherent sources of bias or problems with the approach.

Users of LLMs may find them to be a nice shortcut to drafting material, but should be wary of factual statements made and read with a careful and critical eye. While LLMs like ChatGPT have a lot of uses, providing deep commentary or useful policy analysis is not one of those uses, for now.

Here's how ChatGPT handled the assignment of writing about the pandemic:

Prompt: What are some key take aways from the COVID-19 pandemic?

“The COVID-19 pandemic has had a profound impact on individuals, societies, and the global community as a whole. Here are some key takeaways that have emerged from this crisis:

  • The importance of public health infrastructure: The pandemic has highlighted the critical role of public health infrastructure in preventing and responding to outbreaks. Countries with robust health care systems and effective public health measures, such as testing, contact tracing, and vaccination campaigns, have generally fared better in controlling the spread of the virus.
  • The importance of scientific research and innovation: The rapid development of vaccines and therapeutics to combat COVID-19 is a testament to the power of scientific research and innovation. The pandemic has also underscored the need for continued investment in scientific research to better understand the nature of infectious diseases and to develop new treatments and preventive measures.
  • The impact of social and economic inequality: The pandemic has exposed and exacerbated existing social and economic inequalities, with marginalized communities and vulnerable populations disproportionately affected by the virus. This has highlighted the need for policies that address social and economic inequality and prioritize the health and well-being of all individuals.
  • The need for global cooperation: The pandemic has shown that infectious diseases do not respect national borders and require a coordinated global response. It has highlighted the need for international cooperation in sharing information, resources, and expertise to control the spread of the virus and mitigate its impact on health and the economy.
  • The importance of personal responsibility: The pandemic has demonstrated the importance of personal responsibility in preventing the spread of infectious diseases. Measures such as mask-wearing, physical distancing, and hand hygiene can all help reduce the transmission of the virus and protect vulnerable populations. Vaccination is also an important tool in preventing the spread of the virus and reducing its impact on individuals and society.”

Carter C. Price is codirector of the Center for Scalable Computing and Analysis, research quality assurance manager for the Homeland Security Research Division, and a senior mathematician at the nonprofit, nonpartisan RAND Corporation.

This commentary originally appeared on United Press International on May 8, 2023. Outside View © 2023 United Press International.