Project Milestone 3: Rough Draft

At this stage you will be starting to wrap things up. Again, be sure to read the appropriate section for your project type to learn more about the requirements for this milestone.

Demo: Build a novel interactive experience

You should have a semi-working system in place. For this deliverable, you will need to share a 5-10 minute video showing the various components of what you have working so far. Not everything needs to be completed. You are allowed to have placeholders in the code for components that are incomplete. For this reason, we are asking you to submit a video instead of having you write a report and us trying to run the code ourselves.

Your video should include the following things:

1. Description: A high-level description of the your system.
   • What have you been making?
   • What will it be like? (e.g., What do you imagine people will use this tool for? or What sort of game/experience will this be?)
2. Algorithm Explanation: An explanation of the algorithm(s)/model(s) of the system, while showing the code for them.
   • Be sure to include plenty of details where relevant, such as: how you are using the models, what prompts you use, what symbolic components you are using, or how you are using datasets or knowledge bases. Feel free to use anything you wrote about from the Back End Details of your previous milestone.
3. End-to-end Example: An example of how it looks or will look when someone uses your system. (For example, a playthrough of part of your game.)
   • This is basically showing the interface and demonstrating how all of the pieces go together; i.e., the Front End section from Milestone 2 but in video format.

You do not need to talk about your inspirations for the project at this stage, unless you think they are relevant. The video does not need to include a slide show unless you feel that it will improve your explanation of the system.

In a separate document called team#-supplement.pdf, include:

1. Title: What are you calling your system?
2. System Diagram: This might be in something formal like UML or a more informal format, but it should include more details than your Back End Architecture diagram(s) from the previous milestone probably had.
3. Team Members: Give a list of the students who are participating in this project, and what contributions you have made and expect to make for the project.
   • In this section also mention what you have completed so far and what is still left to do.
4. LLM Use Statement: Describe exactly how you used LLMs to generate parts of your code (refer to the syllabus for guidance). If you did not use any generative text, please state so in this section.

Grading

What to Submit

Submit the following to Blackboard:

• The link to your repository.
• Your video or a link to where your video is hosted.
• team#-supplement.pdf

Paper: Attempt to answer a research question about text generation or interactive fiction

To help you, here are some example reports from previous classes:

• Example Report 1
• Example Report 2
• Example Report 3

For this milestone, you will take the components of your proposal and begin to move them into more “paper-like” sections. You will also be adding in some more details.

Your paper needs to be in a conference template, written in LaTeX.

• You can use Overleaf to write LaTeX papers together. The CSEE department has a subscription to Overleaf now, so you should be able to have multiple collaborators on the same paper.
• If you do not have a conference/workshop in mind, I recommend that you use the template from the Association for Computational Linguistics.

Your paper should include the following sections:

Discussion and Conclusion sections will be added in the final deliverable.

1. Title: What are you calling your study?
2. Abstract: A high-level overview of what the paper is about.
3. Introduction: What research question(s) or problem are you trying to solve?
   • Why this it worth researching?
   • What contributions does this work make? (i.e., What are you doing that’s novel?) You might have to compare to other research.
4. Related Work: What previous research has been done on this research question?
   • I want you to do a deeper dive of the related work now. Find at least five more papers to add to the narrative you’ve written so far.
5. Methods: What are you doing or making to address your research question(s)?
   • If you are using any datasets, does the needed data already exist? If so, how much data is available? What does the data look like? If you are just using a few examples for few-shot prompting, how did you select those?
   • Describe your solution to the problem/research question. What model(s) are you using? If you are using few- or zero-shot prompting, what do your prompts look like?
6. Evaluation: Renamed from Experiments section What experiments will you be running?
   • What are you measuring and why? What evaluation metrics do you plan to use to answer your research question(s)?
   • What are your proposed baselines? (That is, what are you comparing your method against?)
   • How do these experiments answer your research questions?
7. Results: What did you find from your evaluation?
   • This should be more than just a list of raw numbers. You should explain to the reader how to interpret any graphs or tables you have and describe any trends that you see.
   • It’s okay if you don’t have all of your results yet! Just report what you have so far.
8. References: Papers are cited correctly in the conference’s format and are references in the main text.

In a separate document called team#-supplement.pdf, write:

1. Team Members: Give a list of the students who are participating in this project, and what contributions you have made and expect to make for the project.
   • In this section also mention what you have completed so far and what is still left to do.
2. LLM Use Statement: Describe exactly how you used LLMs to generate parts of your paper (refer to the syllabus for guidance). If you did not use any generative text, please state so in this section.

Grading

What to Submit

Submit the following to Blackboard:

• team#-roughdraft.pdf which is your draft.
• team#-supplement.pdf, the supplemental material mentioned above.