Perplexity: An AI Tool Meant to Assist Individuals with Research

A logo for Perplexity
Awa-abuon, J. (2024). Perplexity - MakeUseOf. [Photograph].Google Images.

What is Perplexity?

Perplexity provides summaries of any article or webpage, sharing the information most relevant to a user's search. It's useful for quickly understanding the key points of lengthy documents or getting a concise overview of complex topics.

How can I use Perplexity?

Perplexity has many uses, including:

  • Serving as an alternative search engine: Perplexity AI is a search engine that provides answers to questions using natural language queries. It can answer a wide range of questions, from simple to complex and open-ended.
  • Locating research articles: Perplexity AI can be used as a research partner to help users find the information they need.
  • Personal knowledge enhancement: Perplexity AI can be used to enhance personal knowledge by collocating information resources pertaining to a prompt provided to it by the user.
  • Summarization: Perplexity AI can be used to summarize the key points of lengthy documents or get a concise overview of complex topics.

Watch the following video to learn more about the uses and applications of Perplexity:

Why should I take care when using Perplexity?

While generative AI tools like Perplexity can help users with such tasks as locating research articles, organizing existing information, mapping out scholarly discussions, or summarizing sources, the outputs they provide are not always entirely factual or grounded in the best research strategies. To the contrary, Perplexity has been known to hallucinate, or "describe false information created by the AI system to defend its statements." Oftentimes, Perplexity will generate outputs without qualifying the accuracy of the information it provides, and it has been known to confidently provide responses to queries that nonetheless consist of partially or fully fabricated citations or facts.

Additionally, generative AI tools like Perplexity sometimes will provide outputs that lack currency, as some of the large language models that they are trained on lack access to the latest research in a given field of study. In some instances, the information that Perplexity will consult to provide a summary of extant research will be based on old datasets, thereby causing it to frame the information it shares as current when, in reality, it is not.

The use of generative AI tools like Perplexity in academia has also raised many concerns about academic integrity and the respect of intellectual property. One area of academic integrity affected by generative AI tools like Perplexity is that of false citations.

Providing false citations in research, whether one intends to or not, is a violation of St. Catherine University's academic integrity policy. Generative AI tools such as Perplexity have been known to generate false citations, and even if the citations are based on actual papers, the cited content in Perplexity might still be inaccurate, placing the onus of interrogating the accuracy of it on the user of the AI tool.

Where can I find more information about Perplexity?

For more information on Perplexity, please refer to the FAQ page for the generative AI tool.

References

Georgetown University Library. (2024, November 21). Artificial intelligence (generative) resources: Ethics in AI. Click this link to view this resource

Last updated December 4, 2024

Back to top

More Information

Prompt Literacy in Academics

An overview of how to write specific and detailed prompts to optimize the use of AI in research.

Fabrication and Errors in the Bibliographic Citations Generated by ChatGPT

An analysis of the frequency with which AI hallucinates and creates false representations of scholarly work.

How AI Can Help Weed Out Faulty Scientific Research

A reflection on the potential of AI to help forecast the replicability of research studies.

AI in the News

Will AI kill Google? Past Predictions of Doom Were Greatly Exaggerated

A look at the probability of research AI becoming a superior alternative to Google as a search tool.

Use of AI Is Seeping Into Academic Journals—and It’s Proving Difficult to Detect

A review of the challenges of identifying fraudulent research created by AI.