Identifying artificially generated creative writing

Large Language Models (LLM) have found many uses, such as chatbots for customer support or helping to debug code. However, these models have also been misused, for example by generating fake news stories to spread misinformation. The ability to detect machine-generated content would help address the harm caused by the misuse of LLMs. 

Prior research has focused on the identification of deceptive text in a variety of areas, including phishing attempts, fake product review, and academic plagiarism. There is, however, little research on identifying other forms of generated text such as automatic translations, or text that has been reworded by ‘essay assistant’ software. 

Notably, the literature shows that creative writing has rarely been considered, although automatic generation of texts such as poems, songs and novels could cause economic harm to creative artists, and may lead to a reduction in quality of the works available. Therefore, this project will focus on characterising the differences between human generated and machine generated text in the domain of creative writing, and construct a classifier to distinguish reliably between human and AI generated text. 

Academic qualifications

A first-class honours degree, or a distinction at master level, or equivalent achievements ideally in Artificial Intelligence, Computer Science, Statistics.  

English language requirement

If your first language is not English, comply with the University requirements for research degree programmes in terms of English language.

Application process

Prospective applicants are encouraged to contact the supervisor, Dr Peter Barclay ([email protected]) to discuss the content of the project and the fit with their qualifications and skills before preparing an application. 

Contact details

Should you need more information, please email [email protected].

The application must include: 

Research project outline of 2 pages (list of references excluded). The outline may provide details about

• Background and motivation, explaining the importance of the project, should be supported also by relevant literature. You can also discuss the applications you expect for the project results.
• Research questions or
• Methodology: types of data to be used, approach to data collection, and data analysis methods.
• List of references

The outline must be created solely by the applicant. Supervisors can only offer general discussions about the project idea without providing any additional support.

• Statement no longer than 1 page describing your motivations and fit with the project.
• Recent and complete curriculum vitae. The curriculum must include a declaration regarding the English language qualifications of the candidate.
• Supporting documents will have to be submitted by successful candidates.
• Two academic references (but if you have been out of education for more than three years, you may submit one academic and one professional reference), on the form can be downloaded here.

Applications can be submitted here. To be considered, the application must use:

• the advertised title as project title 

Download a copy of the project details here