AI: Student Guide to ChatGPT: Fact checking is always needed

Fact-checking is always needed

AI "hallucination"
The official term in the field of AI is "hallucination." This refers to the fact that it sometimes "makes stuff up." This is because these systems are probabilistic, not deterministic.
 

Web search results as grounding
When an AI model is combined with a search engine, it hallucinates less. That's because it can search the web, read the pages it finds, and use the AI model to summarize those pages, with links to the pages. It may sometimes make a mistake in the summary, so it's always good to follow the links to the web results it found.

Some examples:

• Perplexity AI
• Microsoft Copilot
• Google Gemini
• ChatGPT (with the search button activated)

Scholarly sources as grounding
There are AI systems that combine language models with scholarly sources. These models use scholarly papers as a source of grounding, which makes them more factual.

Some examples:

• Elicit
  A research assistant using language models to automate parts of researchers’ workflows. Currently, the main workflow in Elicit is Literature Review. If you ask a question, Elicit will show relevant papers and summaries of key information about those papers in an easy-to-use table. 
• Consensus

  A search engine that uses AI to search for and surface claims made in peer-reviewed research papers. Ask a plain English research question, and get word-for-word quotes from research papers related to your question. The source material used in Consensus comes from the Semantic Scholar database, which includes over 200M papers across all domains of science.