Mollie Jordan

Mollie Jordan

Auto-generated profile, based on publicly available information

Mollie Jordan

North Carolina State University, Raleigh, NC, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 March 2024
Verified
Conference Paper
Open access
MJMollie Jordan
Mollie Jordan
KLKevin Ly
Kevin Ly
ARAdalbert Gerald Soosai Raj
Adalbert Gerald Soosai Raj
Large language models (LLMs) like ChatGPT are changing computing education and may create additional barriers to those already faced by non-native English speakers (NNES) learning computing. We investigate an opportunity for a positive impact of LLMs on NNES through multilingual programming exercise generation. Following previous work with LLM exercise generation in English, we prompt OpenAI GPT-3.5 in 4 natural languages (English, Tamil, Spanish, and Vietnamese) to create introductory programming problems, sample solutions, and test cases. We evaluate these problems on their sensibility, readability, translation, sample solution accuracy, topicality, and cultural relevance. We find that problems generated in English, Spanish, and Vietnamese are largely sensible, easily understood, and accurate in their sample solutions. However, Tamil problems are mostly non-sensible and have a much lower passing test rate, indicating that the abilities of LLMs for problem generation are not generalizable across languages. Our analysis suggests that these problems could not be given verbatim to students, but with minimal effort, most errors can be fixed. We further discuss the benefits of these problems despite their flaws, and their opportunities to provide personalized and culturally relevant resources for students in their native languages.

3 July 2024
Verified
Conference Paper
Open access
IMIsmael Villegas Molina
Ismael Villegas Molina
AMAudria Montalvo
Audria Montalvo
SZShera Zhong
Shera Zhong
MJMollie Jordan
Mollie Jordan
ARAdalbert Gerald Soosai Raj
Adalbert Gerald Soosai Raj
In the United States, culturally relevant computing (CRC) is one of the most popular pedagogical implementations for Latin American (Latine) students. Culturally-relevant learning resources are a valuable tool for implementing CRC. However, the traditional method of creation and maintenance of textbooks takes a significant amount of time and effort. Given the duration required for textbook production, the development of culturally-relevant learning resources may become lengthened, as it requires close attention both on the material and the incorporation of cultural referents. In order to accelerate the process, we used the advancement of large language models (LLMs) to our advantage. Through prompt engineering, we created a series of prompts to produce a textbook for an introductory computer science course (CS1) that incorporates Latine culture. This textbook was evaluated on metrics regarding sensibility, correctness, readability, linguistic approachability, appropriateness of examples, and cultural relevance. Overall, the generated textbook was mainly sensible, correct, readable, and linguistically approachable. Code examples were not always appropriate due to the usage of libraries that are not typically used in a CS1 course. The cultural relevance was apparent, but it often included surface-level cultural referents. The main incorporation of culture was through geographical locations and people's names. This suggests that the use of LLMs to generate textbooks may serve as a valuable first step for writing culturally-relevant learning resources. Though this study focuses on Latines, our results and prompts may be applicable for generating culturally-relevant CS1 textbooks for other cultures.