Revolutionizing Educational Assessment: The Role of Bing Chat GPT-4 Chatbot in Increasing Efficiency in Grading Open-Ended Questions
Diane Abadam-Eremeev, Rachel P Seng, Janani Srinivasan, Kyle Knouna, Joseph R Bogaudo, Paulo A Rodriguez De La Nuez, Alexey Podcheko · 2025
Read Revolutionizing Educational Assessment: The Role of Bing Chat GPT-4 Chatbot in Increasing Efficiency in Grading Open-Ended Questions by Diane Abadam-Eremeev, Rachel P Seng, Janani Srinivasan, Kyle Knouna, Joseph R Bogaudo, Paulo A Rodriguez De La Nuez, Alexey Podcheko (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12857850.txt.
Description
Diane Abadam-Eremeev and colleagues test a chatbot as a grader for open exam answers, in work from 2025. Schools weigh AI help to speed marking, yet open answer grading needs proof of fairness. Consistency is the key test: same answer should earn the same score each time round.
Twenty-one medical students answered five licensing style open questions for the study. Six chatbot accounts and six faculty members each graded every student answer set. Both groups held fairly steady, but faculty scores spread more between graders. Chatbot grades tracked faculty grades closely on most question types in the set. One mixed recall and use question split the two groups by a firm gap.
Catalog record
| CREATOR | Diane Abadam-Eremeev, Rachel P Seng, Janani Srinivasan, Kyle Knouna, Joseph R Bogaudo, Paulo A Rodriguez De La Nuez, Alexey Podcheko |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |