MG as your master thesis supervisor?

Drawing by Paolo Ghelfi

This page is for the students who are considering having Michele Govenatori (MG) as their master thesis supervisor

What the aim of a dissertation is

Writing an essay, whether it is a literature review or an empirical research, requires adopting critical thinking drawing from the knowledge acquired throughout your study journey so far.

While the final essay may sometimes serve as reference for further analysis or applications, its main purpose is checking the student’s ability to think critically, consistently, creatively.

Using AI to write an essay

Large Language Models (LLMs) are and will increasingly be available. They can be effective for literature research and even for correcting or drafting a text. However, in my experience the key to mastering such tools is having a deeper understanding of the topic at hand, especially its trends and implications.

Although LLMs are improving rapidly, they still tend to write in a shallow, optimistic, predictable, recursive, bombastic way. Phrases like “pivotal importance” sound as typical benchmarks of use of LLM. Current LLMs (at least the cheapest ones) tend to imitate the way lousy human authors write: repeating clichés to avoid taking risks.

I have no choice but to give low grades to essays suspected of being written with LLMs unless I get substantial evidence of critical or creative thinking when interacting with the student. Unfortunately, such interaction is typically very limited (see next chapter).

How much time MG can allocate to your thesis supervision

Very little. I am sorry to say this, but I get far more supervision requests than I can manage effectively, not to mention the co-supervision jobs. While I am grateful for the trust the students place in me, I need to be honest: you will need to be extremely autonomous.

Here is a list of things I will not be able to provide as a supervisor:

1) Recursive text reading. I can only read once and will provide feedback when I see relevant issues. I expect you to address these issues thoroughly and critically, making the necessary changes and answering my questions.

2) Comprehensive editing. I will only highlight a specific category of issues once. It is your responsibility to apply my suggestions consistently throughout your work.

3) Literature check. I cannot verify all citations. Beware some LLMs make up literature. I do not mind how many papers you mention. I mind how meaningfully you do so. 

Automatic checks on authenticity and non-LLM use can fail. I will mostly base the assessment on my (limited and also fallible) experience. The more you write clichés, the more the text is recursive, obvious, generic, the higher the risk you get a low grade, including by mistake. So simply avoid it: be creative, use your own language, make choices, take risks.

The research question (RQ): set it, follow it.

No essay can effectively test your proficiency unless your research question (RQ) is clearly and precisely set at the beginning. You should dedicate more effort to this than you might think. If the RQ is vague or too broad, it will be ineffective.

Please do not let me read long introductory chapters. Go straight to the point. There is plenty of introductory stuff everywhere. The more I find myself bored while reading, the lower my grade recommendation will be to your graduation commission.