Skip to content

AI-lab-grading-nlp/Formative-feedback

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 

Repository files navigation

Formative feedback

About the project

Experiments with localized versions of AI models to find fast short-answer response feedback methods.

Requirements

Prerequisites

Python 3.8+ is required.

Installation

Clone the repository.

git clone https://github.com/github_username/repo_name.git

Usage

  1. Add the question, the rubric, and a student's answer into the "prompt."
  2. Run the model.
  3. Observe the output: the model's feedback based on the information provided in the rubric.

Roadmap

  1. The project would assign feedback to a poll response using a large language model.
  2. A technology that has been used so far is BigScience's BLOOM.
  3. Future directions would include experimenting with prompt engineering in BLOOM to develop accurate feedback and potentially combining the LLM with the classification model overviewed in the separate repository.

About

Experimenting with large language models and their capabilities in giving complex formative feedback on top of explaining the intuition behind a label

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors