Library › Study AI › College students

Label each sentence of a chatbot summary against the abstract

  • For College students
  • You practice Catching mistakes and made-up facts
  • Time about 5 minutes
  • Level Advanced

About this exercise

A chatbot summarized a study for your paper. Compare each of its 4 sentences with the abstract. Get exactly 4 numbered lines, each labeled Faithful, Overstated or Invented followed by a reason under 12 words, judged only by the abstract. Plain text, under 90 words.

Common mistakes when you ask AI for this

  • Trusting the summary. The chatbot sounds confident, so the AI agrees with it. Try: Say: "Judge each sentence only by the abstract."
  • Mixing up overstated and invented. Overstated stretches a real finding; invented adds something not in the abstract. Try: Add: "Overstated = stretches a real finding. Invented = not in the abstract."
  • No label rules. Without exact labels you get paragraphs of commentary. Try: Say: "Each line starts with Faithful, Overstated or Invented."
  • Long reasons. The AI explains each at length. Try: Say: "Reason under 12 words."
  • Not saying how many lines. The AI picks its own number, and it usually picks more than you need. Try: Be exact: "Exactly 4 numbered lines."
  • Trusting the AI to count words. AI is bad at counting. Ask for a total and it often lands 20% over. Try: Cap each part: "each line under 12 words."
  • Forgetting where it's going. AI formats for a screen, with bold and headings that show up as stray symbols. Try: Say: "Plain text, no bold, no headings."

What a strong prompt includes

  • Says how many lines
  • Gives the three labels
  • Defines the labels
  • Uses the abstract only
  • Limits the reasons

Practice this now ↑

Related exercises