File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CSEET58097.2023.00028
- Scopus: eid_2-s2.0-85173599193
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Toward AI-assisted Exercise Creation for First Course in Programming through Adversarial Examples of AI Models
| Title | Toward AI-assisted Exercise Creation for First Course in Programming through Adversarial Examples of AI Models |
|---|---|
| Authors | |
| Keywords | adversarial example ChatGPT exercise mutation |
| Issue Date | 31-Aug-2023 |
| Abstract | We propose a new methodology, the Exercise Creation Methodology (ECM), that leverages recent AI technology advancements to create ChatGPT-assisted programming exercises for beginners. ECM takes an existing exercise as input and mutates it by removing some contents into semantically equivalent but syntactically different versions. The pair of versions are labeled as answered correctly and misleadingly by ChatGPT. The removed contents are re-inserted incrementally with further mutation, ensuring the labels remain unchanged. Using the version with the misleading answer and the ChatGPT elaboration on the other version, we construct a ChatGPT-assisted exercise. The latter version may also serve as a solution. We illustrate ECM using a case study. |
| Persistent Identifier | http://hdl.handle.net/10722/357299 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Chan, W K | - |
| dc.contributor.author | Yu, Y T | - |
| dc.contributor.author | Keung, Jacky W | - |
| dc.contributor.author | Lee, Victor CS | - |
| dc.date.accessioned | 2025-06-23T08:54:36Z | - |
| dc.date.available | 2025-06-23T08:54:36Z | - |
| dc.date.issued | 2023-08-31 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/357299 | - |
| dc.description.abstract | <p>We propose a new methodology, the Exercise Creation Methodology (ECM), that leverages recent AI technology advancements to create ChatGPT-assisted programming exercises for beginners. ECM takes an existing exercise as input and mutates it by removing some contents into semantically equivalent but syntactically different versions. The pair of versions are labeled as answered correctly and misleadingly by ChatGPT. The removed contents are re-inserted incrementally with further mutation, ensuring the labels remain unchanged. Using the version with the misleading answer and the ChatGPT elaboration on the other version, we construct a ChatGPT-assisted exercise. The latter version may also serve as a solution. We illustrate ECM using a case study.</p> | - |
| dc.language | eng | - |
| dc.relation.ispartof | 2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T) (07/08/2023-09/08/2023, Tokyo, Japan) | - |
| dc.subject | adversarial example | - |
| dc.subject | ChatGPT | - |
| dc.subject | exercise | - |
| dc.subject | mutation | - |
| dc.title | Toward AI-assisted Exercise Creation for First Course in Programming through Adversarial Examples of AI Models | - |
| dc.type | Conference_Paper | - |
| dc.identifier.doi | 10.1109/CSEET58097.2023.00028 | - |
| dc.identifier.scopus | eid_2-s2.0-85173599193 | - |
| dc.identifier.volume | 2023-August | - |
| dc.identifier.spage | 132 | - |
| dc.identifier.epage | 136 | - |