Generative AI: AI Tools for Research

Understanding AI Capabilities:

• AI tools excel in certain tasks but face challenges in others.
• ChatGPT is proficient in creating natural-sounding sentences.
• But it Struggles with math tasks and tends to generate fictitious sources when asked for citations.

Prompt Engineering Techniques:

• Experiment to find the most effective prompts for your goals.
• Common techniques include:
  • Clearly and concisely defining the expected output.
  • Providing necessary information to be included in the response.
  • Briefly explaining a theory or desired style before making a query.
  • Requesting output in a specific style or format (e.g., "write a fairy tale," "respond as Elon Musk," "in the style of Frida Kahlo").
  • Offering examples of the expected task before the query.

Fine-tuning Output:

• For complex queries, use multiple follow-up queries to refine the output.
• Act as a co-editor, explicitly instructing ChatGPT on desired changes to the draft.

Fact-checking Claims:

• Results from language-based generative AI may not always be factually correct.
• Verify results against personal knowledge and other sources.
• AI does not eliminate the need for lateral reading, checking multiple sources, and critical thinking.

AI tools for research can help you to discover new sources for your literature review or research assignment. These tools will synthesize information from large databases of scholarly output with the aim of finding the most relevant articles and saving researchers' time. As with our research databases or any other search tool, however, it's important not to rely on one tool for all of your research, as you will risk missing important information on your topic of interest.