| Departments |
Computer Science, Zienkiewicz Institute for Modelling, Data and AI
|
|---|
| Description | In the US, to become a lawyer, a Bar Exam must be taken and past. The Bar Exam consists of 200 multiple choice questions, covering an extensive range of legal topics. The task in the project is to classify the questions in the Bar Exam and to design a system to pass the Bar Exam, using techniques from NLP, logic, and machine learning. There is prior work in this area to study and extend. |
|---|
| Preparation | Some literature:
LLMs did well on the Bar Exam
https://law.stanford.edu/2023/04/19/gpt-4-passes-the-bar-exam-what-that-means-for-artificial-intelligence-tools-in-the-legal-industry/
https://royalsocietypublishing.org/doi/10.1098/rsta.2023.0254
LLMs didn't do so well on the Bar Exam:
https://link.springer.com/article/10.1007/s10506-024-09396-9 |
|---|
| Project Categories |
Artificial Intelligence (AI), January Cohort, Law |
|---|
| Project Keywords |
|
|---|
Level of Studies
|
| Level 6 (Undergraduate Year 3) |
yes
|
|---|
| Level 7 (Masters) |
yes
|
|---|
| Level 8 (PhD) |
yes
|
|---|