Why choose this project topic?
A study of answering institutional questions using only a reviewed document collection gives this topic a concrete purpose beyond simply adding an AI model. Comparing answer grounding, citation accuracy and unsupported response rate helps a student demonstrate capability, inspect failure cases and explain where human review or a simpler method remains necessary.
How effectively can grounded campus faq assistant support answering institutional questions using only a reviewed document collection, evaluated using answer grounding, citation accuracy and unsupported response rate?
Choose a feasible licensed or synthetic dataset and available compute budget, then agree a narrow evaluation for answering institutional questions using only a reviewed document collection with your supervisor.
Proposed project objectives
- 01Define the task, evidence and evaluation assumptions for answering institutional questions using only a reviewed document collection.
- 02Create fictional campus policies, build retrieval-based answering and evaluate supported answers, source citations and refusal when evidence is absent.
- 03Measure answer grounding, citation accuracy and unsupported response rate against a stated baseline and analyse failure cases.
A suggested research approach
Create fictional campus policies, build retrieval-based answering and evaluate supported answers, source citations and refusal when evidence is absent. Check dataset permissions and keep evaluation examples separate from model development. Record model versions, prompts or training settings, then compare answer grounding, citation accuracy and unsupported response rate using repeatable runs and retain incorrect outputs for a transparent limitations discussion.
What you will need
- Fictional policy documents
- Retrieval model
- Reviewed question-answer test set
Keep your project scope clear
The assistant must not invent institutional rules or present generated answers as official advice. Generated project writing does not include a trained or deployed AI application.
Artificial Intelligence project chapter outline
Use this outline as a starting point. You can edit the chapter titles to match your department’s format during setup.
- Chapter 1Introduction
- Chapter 2Literature Review
- Chapter 3System Analysis and Design
- Chapter 4System Implementation and Testing
- Chapter 5Summary, Conclusion and Recommendations
Turn this topic into your own final year project.
Your title, department, research question and outline are ready. Add your institution, personalise the details and continue to your project workspace.
Generate the Complete Project Generation uses your word balance. Review the draft and supply your own verified research findings.