This repository is intedned to contain a collection of notes and paper summaries for each class of the Reponsible AI course tought at UVA in the Fall-24. The course is organized around six topics:
- Fairness
- Safety
- Privacy
- Evaluation
- Unlearning
- Misuse of AI and Governance
Each topic is associated with the corresponding folder in this repository.
Students should should write the report on the papers and topics reviewed in their class by modifying the associated ".md" file.
This is a tentative calendar and it is subject to change.
Date | Topic | Subtopic | Blog |
---|---|---|---|
Wed Feb 5 | Fairness | Intro and bias sources | Group 1 |
Mon Feb 7 | Fairness | Statistical measures | Group 2 |
Wed Feb 12 | Fairness | Tradeoffs | Group 3 |
Mon Feb 14 | Fairness | LLMs: Toxicy and Bias | Group 4 |
Wed Feb 19 | Fairness | LLMs: Fairness | Group 5 |
Mon Feb 21 | Fairness | Policy aspects | Group 6 |
Mon Feb 26 | No class (AAAI) | ||
Wed Feb 28 | Safety | Distribution shift | Group 1 |
Wed Mar 6 | Spring break | ||
Mon Mar 11 | Spring break | ||
Mon Mar 11 | Safety | Poisoning | Group 2 |
Wed Mar 13 | Safety | Adversarial Robustness | Group 3 |
Mon Mar 18 | Safety | Adversarial Robustness | Group 4 |
Wed Mar 20 | Safety | LLMs: Prompt injection | Group 5 |
Mon Mar 25 | Safety | LLMs: Jailbreaking | Group 6 |
Mon Mar 25 | Privacy | Differential Privacy 1 | Group 1 |
Wed Mar 27 | Privacy | Differential Privacy 2 | Group 2 |
Mon Apr 1 | Privacy | Auditing and Membership inference | Group 3 |
Wed Apr 3 | Privacy | Privacy and Fairness | Group 4 |
Mon Apr 8 | Privacy | LLMs: Private issues in LLMs | Group 5 |
Wed Apr 10 | Privacy | LLMs: Privacy in LLMs | Group 6 |
Mon Apr 15 | Evaluation | Model cards | Group 1 |
Wed Apr 17 | Evaluation | LLMs: evaluation | Group 2 |
Mon Apr 22 | Unlearning | Unlearning 1 | Group 3 |
Wed Apr 24 | Unlearning | LLMs: Targeted unlearning | Group 4 |
Mon Apr 29 | Misuse of AI and Governance | Group 5 |
Expectations:
- Each group will reivew all paper from the provided list, and they may propose additional ones for approval.
- Summaries should be written in Markdown format (supporting images and formulas) and committed to the course's GitHub repository.
- The summary should include the following sections: Introduction and Motivations, Methods, Key Findings, and Critical Analysis.
- The Critical Analysis section should evaluate the strengths, weaknesses, potential biases, and ethical considerations of the paper.
- Summaries must be submitted four days prior to the presentation for review and potential feedback.
Assessment Criteria:
- Clarity and coherence of the written summary.
- Depth of critical analysis and understanding of the paper's content.
- Proper use of formatting and adherence to submission guidelines.
- Timeliness of submission.