Investigating Sampling Impacts on an LLM-Based AI Scoring Approach: Prediction Accuracy and Fairness

Author(s):

Zhang, Mo; Johnson, Matthew S.; Ruan, Chunyi

Publication Year:

2024

Source:

Journal of Measurement and Evaluation in Education and Psychology, v15 p348-360, 2024

Document Type:

Article

Page Count:

13

Subject/Key Words:

Artificial Intelligence, Large Language Models (LLM), Fairness, Accuracy, Bidirectional Encoder Representations from Transformers (BERT), Prediction, Automated Scoring, Sampling

Read More

• https://doi.org/10.21031/epod.1561580