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 and writing. 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 large collections of text to generate human-like responses
- Predict the next word (token) based on statistical patterns
- Do not “think” or “understand” like humans
- Mimic intelligence, but are not truly “intelligent”; can be very convincing
Key concept
- LLMs work by estimating probability relationships among tokens, not by indexing content like a database such as Wikipedia
Key terms
- Token: basic unit for LLMs to process information
- Prompt: user input
- Session: a series of user input and LLM output
- Memory: context retained within a session; some systems support cross-session memory

Limitations and biases exist in both the training data and the model development process
- English is the dominant language
- Often optimized to be agreeable and non-confrontational
- Limitations of human knowledge and available text data sets
LLMs cannot assess the quality of sources
- Cannot reliably distinguish between high- and low-quality content
- Cannot 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)
For scientific writing
- May not be suitable to process novel findings; summarizing and explaining existing knowledge may work better

Use LLMs as tools to sharpen your thinking, not black boxes for quick answers
LLMs do not necessarily save time; more useful for deepening the thinking process, which often takes more time
LLMs may not save time
- In fact, LLMs are most valuable when used to deepen the thinking process, which takes more time and effort
LLMs act like mirrors; their responses reflect your input and framing
- Trained to be agreeable, they often conform to both your explicit instructions and implicit tone
Suggested practice
- Start with a solid frame of reference
  - Provide clear context for the task, including your goals and expectations
  - What exactly do you want to obtain?
  - How do you want the LLM to act?
  - Are your expectations realistic?
  - Examples of possible uses (varying in feasibility and reliability):
    - Polish arguments
    - Organize thoughts
    - Brainstorm new ideas
    - Identify major gaps in reasoning
    - Provide critical review
- Assess the output, make decisions, and provide feedback
- Use an iterative process; may involve gradual refinement or drastic changes
- Know when to stop

LLMs are designed to mirror your tone and reinforce your framing
This can lead to overly agreeable responses, especially in extended conversations
Asking LLMs to role-play can be useful
- Not because the roles have true expertise, but because the exercise can stimulate YOUR thinking

LLMs mirror your tone, assumptions, and style
The output can become overly agreeable, particularly in long sessions
- It is natural for you to be defensive when LLMs point out potential issues in your arguments
- Issue: LLMs are too easy to be convinced by your rebuttal
- Reinforcing your biases is not useful
Asking LLMs to role-play can be useful
- Not because the roles have true expertise, but because the exercise can stimulate YOUR thinking
- For example, asking LLMs to be a member of your qualifying committee or a reviewer of your manuscript can help your preparation. But in these scenarios, LLMs likely can mimic the tone and style, but would not have the sufficient depth in relevant knowledge nor the logic of human experts

LLMs mirror your tone, assumptions, and style
Output can become overly agreeable, especially in long sessions
- It is natural to feel defensive when an LLM points out flaws in your argument
- However, LLMs are easily swayed by your rebuttals
- Reinforcing your own biases is not useful
Asking LLMs to role-play can be useful
- Not because the roles provide true expertise, but because the exercise can stimulate YOUR thinking
- For example, asking an LLM to act as a qualifying committee member or manuscript reviewer may help you prepare
- In these roles, LLMs can mimic tone and style, but they lack the knowledge, logic, and judgement of human experts

“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”?