Human-AI Collaboration for High-Stakes Text Production

About the Project

Project Description

As Artificial Intelligence (AI) systems (such as Large Language Models) are increasingly used to support high-stakes text production, understanding how humans and AI systems should collaborate becomes critical. In many real-world settings, full automation is neither desirable nor acceptable, and responsibility must remain with human decision-makers. This PhD project investigates human-AI collaboration as a central design and evaluation challenge in Natural Language Processing (NLP).

The project focuses on interaction patterns, responsibility allocation, and evaluation of collaborative outcomes, rather than on fully automated text generation. It aims to understand how collaboration between humans and language models can improve quality, reliability, and accountability in text production tasks.

Aims and Methods

The student will design, implement, and study interactive NLP systems in which humans and language models jointly produce, revise, or validate text. Collaboration scenarios may include translation revision, summarisation for decision support, educational content creation, or other domains where accuracy, clarity, and accountability matter.

The research will explore different collaboration strategies, such as AI-first drafting with human revision, human-guided generation, or iterative co-editing. It will examine how these strategies affect both the final outputs and the human participants involved. Evaluation will consider output quality alongside human-centred factors, including trust, cognitive load, error detection, confidence in decisions, and perceived responsibility.

Methods will combine NLP experimentation with user studies, interaction logging, and mixed quantitative and qualitative analysis. The project may also investigate how collaboration strategies should adapt to task complexity, domain risk, or variation in model quality.

Potential application domains include, but are not limited to, education, translation, summarisation, public-sector communication, or social care, and may involve high-resource or low-resource languages. While specific domains may be used as case studies, the project aims to derive general principles for human-AI collaboration in high-stakes NLP applications.

Deliverables (indicative)

• Design patterns for human-AI collaboration in NLP
• Empirical studies comparing collaborative workflows
• Evaluation frameworks capturing both system and human performance
• Prototype tools demonstrating collaborative NLP systems

Keywords

Human-AI collaboration, interactive NLP, high-stakes communication, evaluation

How to Apply

This project is accepting applications all year round, for self-funded candidates.

Mode of Study: Full-time or part-time

Please submit your application via Computer Science and Informatics - Study - Cardiff University

In the funding field of your application, indicate “I am applying for a self-funded PhD in Computer Science and Informatics”, and specify the project title and supervisors of this project in the text box provided.

Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject. Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas.

Applicants must demonstrate English language proficiency. Students who do not have English as a first language must prove this by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component. A full list of accepted qualifications is available here: https://www.cardiff.ac.uk/study/international/english-language-requirements/postgraduate

If you are interested, please contact Dr Fernando Alva Manchego (alvamanchegof@cardiff.ac.uk) sending your CV in the first instance. The application process requires you to develop an individual research proposal jointly with the supervision team, which builds on the information provided in this advert.

Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below.

Please submit your application via Computer Science and Informatics - Study - Cardiff University

In order to be considered candidates must submit the following information:

• In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal. Your research proposal should not exceed 2000 words, including references and bibliography.
• A personal statement (as part of the university application form, or as a separate attachment, if you prefer).
• A CV. Guidance on CVs for a PhD position can be found on the FindAPhD website.
• Qualification certificates and Transcripts - original and English translation, if applicable.
• References x 2 which should be academic references. Please note you need to provide the reference documents as part of your application.
• Proof of English language (if applicable).

Interview– If the application meets all of the entrance requirements listed above, you will be invited to an interview.