tutorials:ai_llm_tools
Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
| tutorials:ai_llm_tools [2025/06/09 14:57] – chkuo | tutorials:ai_llm_tools [2025/06/12 17:40] (current) – [Value] chkuo | ||
|---|---|---|---|
| Line 2: | Line 2: | ||
| ===== About ===== | ===== 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. | + | * A brief guide to using large language models (LLMs) often referred to as artificial intelligence (AI) tools, such as ChatGPT by OpenAI and Gemini by Google, in the context of academic research |
| * Target audience: undergraduate students, graduate students, and postdocs (in biology) | * Target audience: undergraduate students, graduate students, and postdocs (in biology) | ||
| + | |||
| ===== Preface ===== | ===== Preface ===== | ||
| Line 10: | Line 11: | ||
| * As the user, you are responsible for the final output of your work | * As the user, you are responsible for the final output of your work | ||
| * Include proper usage statements | * Include proper usage statements | ||
| - | * For personal use: It is possible | + | * For personal use: |
| + | * Emotional support can be valuable | ||
| + | * Should | ||
| + | * Be careful of potential misuse and harm | ||
| ===== LLMs Explained ===== | ===== LLMs Explained ===== | ||
| - | ==== What? ==== | + | ==== What are LLMs? ==== |
| - | * Artificial intelligence systems trained on vast amounts | + | * Artificial intelligence systems trained on large collections |
| - | * " | + | * Predict |
| - | * Do not "think" | + | * Do not “think” or “understand” |
| + | * Mimic intelligence, | ||
| * Key concept | * Key concept | ||
| - | * Language model (vs. database): | + | * LLMs work by estimating |
| + | * Key terms | ||
| * Token: basic unit for LLMs to process information | * Token: basic unit for LLMs to process information | ||
| * Prompt: user input | * Prompt: user input | ||
| - | * Session: user input + LLM output, | + | * Session: |
| - | * Memory | + | * Good practice: limit the scope and length of individual sessions |
| + | * Memory: information kept from previous interactions; | ||
| + | |||
| + | |||
| + | ==== Value ==== | ||
| + | * Always-available conversation partners | ||
| + | * Often, just having a conversation helps you think much more clearly | ||
| + | * Particularly helpful in the context of emotional support | ||
| + | * In some ways, LLMs are like crystals of human knowledge | ||
| + | * Useful for learning new topics efficiently through interactive Q&A | ||
| + | * Perform especially well on topics with abundant, high-quality training data | ||
| + | * Highly proficient in language, particularly useful for clear and precise expression of ideas | ||
| + | * Great tools for self-improvement | ||
| + | * How much can LLMs be trusted? I don't know | ||
| + | * Have I successfully used LLMs to achieve deeper thinking and clearer writing? YES! | ||
| + | * What's the catch? Time and effort | ||
| ==== Limitations ==== | ==== Limitations ==== | ||
| - | * LLMs cannot assess the quality of information | + | |
| - | * Academia: " | + | * English is the dominant language |
| - | * Outside of academia: biased information from paid advertising and other influence | + | * Often optimized to be agreeable and non-confrontational |
| - | * LLMs do not know what they do not know; may make up false info (AI hallucination) | + | * Limitations of human knowledge and available text data sets |
| - | * Bias in training data set; language | + | |
| + | * Cannot | ||
| + | * Cannot | ||
| + | * Academia: " | ||
| + | * 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 | * For scientific writing | ||
| - | * May not be suitable | + | |
| + | | ||
| + | |||
| + | |||
| + | ==== Common Failure Modes ==== | ||
| + | * Superficial content | ||
| + | * Oversimplification | ||
| + | * Overstatement | ||
| + | * False coherence | ||
| + | * Hallucination; fabricated web links, DOIs, and PubMed IDs | ||
| + | * Non-specific terminology for highly specific topics | ||
| - | ==== Failure Modes ==== | ||
| - | * Common issues: non-specific terminology, | ||
| ===== Core Principles for Usage ===== | ===== Core Principles for Usage ===== | ||
| * Use LLMs as tools to sharpen your thinking, not black boxes for quick answers | * Use LLMs as tools to sharpen your thinking, not black boxes for quick answers | ||
| - | * Using LLMs does not necessarily | + | * Do not outsource your thinking process! |
| - | * Good practice involves: iterate, reflect, calibrate, and finalize | + | * Use LLMs in your thinking and learning: you become better |
| - | * Start with a solid frame of reference. Provide | + | * Use LLMs to think for you: you skip the practice, bad for learning |
| + | * LLMs may not save time | ||
| + | * In fact, LLMs are most valuable when used to deepen | ||
| + | * Explore possibilities, | ||
| + | * Example: You are deciding the title of your manuscript. You provided the abstract, do you ask LLMs to: | ||
| + | * (1) suggest a title, or | ||
| + | * (2) suggest three titles, compare the emphasis | ||
| + | * 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 | ||
| + | * Helpful to make your implicit thoughts become explicit and better organized | ||
| + | * Suggested practice | ||
| + | * Start with a solid frame of reference | ||
| + | * Provide | ||
| * What exactly do you want to obtain? | * What exactly do you want to obtain? | ||
| - | * How do you want to LLM to act? Is your expectation | + | * How do you want the LLM to act? |
| - | * Assess the output, make decision, and provide feedback | + | * Are your expectations |
| - | * Iterative | + | * Examples of possible |
| - | * Knowing | + | * Polish |
| + | * Organize | ||
| + | * Brainstorm | ||
| + | * Identify | ||
| + | * Provide | ||
| + | * Assess the output, make decisions, and provide feedback | ||
| + | * Use an iterative | ||
| + | * Fact check, fact check, and fact check!!! | ||
| + | * Know when to stop; did the last iteration provide meaningful improvement? | ||
| ===== Human–AI Dynamics ===== | ===== Human–AI Dynamics ===== | ||
| - | * By design, | + | * LLMs mirror your tone, assumptions, |
| - | * The output | + | * Output |
| - | * Asking LLMs to role-play can be useful, but mostly | + | * 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 | ||
| + | * 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 Judgment of human experts | ||
| ===== Use Cases ===== | ===== Use Cases ===== | ||
| - | * "Deep Research" | + | * Writing and obtaining feedback as a way of thinking; force LLMs to criticize and challenge your thoughts |
| + | * Use the "Deep Research" | ||
| * Reading dense papers | * Reading dense papers | ||
| - | * Build custom | + | * Build custom |
| * Grammar check and copy editing | * Grammar check and copy editing | ||
| + | * Prepare for discussion with seminar speakers; info about you and the speaker as the input, suggestions of questions to ask as the output | ||
| * Drafting or refining emails (with tone sensitivity) | * Drafting or refining emails (with tone sensitivity) | ||
| - | | + | * Technology related, such as server/ |
| - | | + | |
| - | ===== Other Notable | + | |
| + | ===== Additional | ||
| * Test the tool with topics that you know well first for evaluation | * Test the tool with topics that you know well first for evaluation | ||
| + | * Push boundaries, learn the situations that LLMs are useful (or not) | ||
| + | * Different tools for different uses | ||
| + | * ChatGPT is chatty; highly conversational, | ||
| + | * Gemini integrates Google Search; useful for questions with clear answers and you want the web sources | ||
| + | * Learn to judge output, know when to reject the suggestions | ||
| * Over time, thoughtful use of LLMs can improve your writing, reflection, and decision-making skills | * Over time, thoughtful use of LLMs can improve your writing, reflection, and decision-making skills | ||
| * AI/LLM tools are under intensive development, | * AI/LLM tools are under intensive development, | ||
| - | * In future, AI/LLM may be useful " | + | |
tutorials/ai_llm_tools.1749452260.txt.gz · Last modified: by chkuo