Pragnya Sridhar

Pragnya Sridhar

Auto-generated profile, based on publicly available information

Pragnya Sridhar

Carnegie Mellon University, Pittsburgh, PA, USA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
29 January 2024
Verified
Conference Paper
Open access
JDJacob Doughty
Jacob Doughty
ZWZipiao Wan
Zipiao Wan
ABAnishka Bompelli
Anishka Bompelli
JQJubahed Qayum
Jubahed Qayum
TWTaozhi Wang
Taozhi Wang
MSMajd Sakr
Majd Sakr
There is a constant need for educators to develop and maintain effective up-to-date assessments. While there is a growing body of research in computing education on utilizing large language models (LLMs) in generation and engagement with coding exercises, the use of LLMs for generating programming MCQs has not been extensively explored. We analyzed the capability of GPT-4 to produce multiple-choice questions (MCQs) aligned with specific learning objectives (LOs) from Python programming classes in higher education. Specifically, we developed an LLM-powered (GPT-4) system for generation of MCQs from high-level course context and module-level LOs. We evaluated 651 LLM-generated and 449 human-crafted MCQs aligned to 246 LOs from 6 Python courses. We found that GPT-4 was capable of producing MCQs with clear language, a single correct choice, and high-quality distractors. We also observed that the generated MCQs appeared to be well-aligned with the LOs. Our findings can be leveraged by educators wishing to take advantage of the state-of-the-art generative models to support MCQ authoring efforts.

14 March 2024
Verified
Conference Paper
Open access
AAArav Agarwal
Arav Agarwal
KMKarthik Mittal
Karthik Mittal
ADAidan Doyle
Aidan Doyle
PSPragnya Sridhar
Pragnya Sridhar
ZWZipiao Wan
Zipiao Wan
MSMajd Sakr
Majd Sakr
We conduct a preliminary study of the effect of GPT's temperature parameter on the diversity of GPT4-generated questions. We find that using higher temperature values leads to significantly higher diversity, with different temperatures exposing different types of similarity between generated sets of questions. We also demonstrate that diverse question generation is especially difficult for questions targeting lower levels of Bloom's Taxonomy.

20 September 2021
Verified
Book Chapter
Closed access
PDF file
PSPragnya Sridhar
Pragnya Sridhar
DKDeepika Karanji
Deepika Karanji
GSGambhire Swati Sampatrao
Gambhire Swati Sampatrao
SDSravan Danda
Sravan Danda
SSSnehanshu Saha
Snehanshu Saha