PromptPatrol: Difference between revisions
(Created page with "Mentor: Mick Vermeulen Language models like ChatGPT and Claude.ai are becoming increasingly more popular since their launch. These models affect every line of work, including student assignments. For some assignments, professors require students to hand in authentic work for their own personal development, not for the sake of handing in an assignment. In this project, you will design a system that is able to reliably detect text generated by LLMs in student assignments....") |
No edit summary |
||
| Line 1: | Line 1: | ||
Client: Mick Vermeulen, IMC <Mick.Vermeulen@imc.com> | |||
Language models like ChatGPT and Claude.ai are becoming increasingly | Language models like ChatGPT and Claude.ai are becoming increasingly popular. These models affect every line of work, including student assignments. For some assignments, professors require students to hand in authentic work for their own personal development, not for the sake of handing in an assignment. | ||
In this project, you will design a system that is able to reliably detect text generated by LLMs in student assignments. | In this project, you will design a system that is able to reliably detect text generated by LLMs in student assignments. User experience is a top priority; the system should be fast and simple to use. How will you test, measure or prove this? It should integrate seamlessly with the learning environment of Cambridge. The detection framework could use machine learning, but could an MVP use more simple approaches? What heuristics might determine if text is written by a human? Reports should offer statistics line-by-line, highlighting which parts are human-written or machine-written. | ||
Latest revision as of 10:31, 5 November 2024
Client: Mick Vermeulen, IMC <Mick.Vermeulen@imc.com>
Language models like ChatGPT and Claude.ai are becoming increasingly popular. These models affect every line of work, including student assignments. For some assignments, professors require students to hand in authentic work for their own personal development, not for the sake of handing in an assignment. In this project, you will design a system that is able to reliably detect text generated by LLMs in student assignments. User experience is a top priority; the system should be fast and simple to use. How will you test, measure or prove this? It should integrate seamlessly with the learning environment of Cambridge. The detection framework could use machine learning, but could an MVP use more simple approaches? What heuristics might determine if text is written by a human? Reports should offer statistics line-by-line, highlighting which parts are human-written or machine-written.
