This is an old revision of the document!

AI/LLM Tools

About

A brief guide to using large language models (LLMs), such as ChatGPT by OpenAI and Gemini by Google, which are often referred to as artificial intelligence (AI) tools, in the context of academic research. By Chih-Horng Kuo (chk@gate.sinica.edu.tw). Suggestions are welcome.
Target audience: undergraduate students, graduate students, and postdocs (in biology)

For work: Ethics first!
- Respect the general rules of academic integrity
- As the user, you are responsible for the final output of your work
- Include proper usage statements
For personal use: It is possible and potentially beneficial to use LLMs for emotional support, but should not be mistaken for true care or therapeutic depth. Be careful of potential misuse and harm.

Artificial intelligence systems trained on vast amounts of text data to understand and generate human language
- “Predicting the next word in a sequence based on the training”; this is not “real intelligence”
- Do not “think” like humans do
Key concept
- Language model (vs. database): probability relationships among words (token)
- Token: basic unit for LLMs to process information
- Prompt: user input
- Session: user input + LLM output, combined to generate text
- Memory

LLMs cannot assess the quality of information sources. As a result, they cannot reliably distinguish between high- and low-quality content or apply appropriate weighting.
- Academia: “good” vs. “bad” papers
- Outside of academia: biased information from paid advertising and other influence
LLMs do not know what they do not know; may make up false info (AI hallucination)
Bias in training data set; language
For scientific writing
- May not be suitable to process novel findings; summarizing and explaining existing knowledge may work better

Common issues: non-specific terminology, superficial, overstatement, false coherence, hallucination

Use LLMs as tools to sharpen your thinking, not black boxes for quick answers
Using LLMs does not necessarily save time; more useful to use LLMs to deepen your thinking process (which actually takes more time)
Good practice involves: iterate, reflect, calibrate, and finalize
- Start with a solid frame of reference. Provide sufficient info for the task, as well as your requirement and expectation for the LLM.
  - What exactly do you want to obtain?
  - How do you want to LLM to act? Is your expectation realistic? For example, these are possible but differ in feasibility and reliability: polishing arguments, organize thoughts, brainstorm new ideas, identify major gaps in arguments, and critical review.
- Assess the output, make decision, and provide feedback
- Iterative process; may involve gradual refinement and/or drastic changes
- Knowing when to stop is important

By design, LLMs mirror your tone and reinforce your framing
The output can become too agreeable
Asking LLMs to role-play can be useful, but mostly because the process can stimulate YOUR thinking, not because LLM in different roles truly have different expertises

“Deep Research” function (available in both ChatGPT & Gemini) for targeted search of PubMed and summary
Reading dense papers
Build custom database of selected references using NotebookLM by Google
Grammar check and copy editing
Drafting or refining emails (with tone sensitivity)
To prepare for individual meeting with seminar speakers. Given your interest and the speaker's expertise, suggest a few questions
Technology related, such as server/intranet setup, hardware purchase planning, Linux/NAS configuration, organization of computer files and directories

Test the tool with topics that you know well first for evaluation
Over time, thoughtful use of LLMs can improve your writing, reflection, and decision-making skills
AI/LLM tools are under intensive development, different tools may perform better at different tasks; develop your own taste and workflow, keep an eye on the development
In future, AI/LLM may be useful “simulated advisor”?