Pragnya Sridhar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Pragnya Sridhar has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Aidan Doyle
Carnegie Mellon University, Pittsburgh, PA, USA
2 shared publications - Arav Agarwal
Carnegie Mellon University
2 shared publications - Jacob Arthur Doughty
Carnegie Mellon University, Pittsburgh, USA
2 shared publications - Jaromir Savelka
Carnegie Mellon University, Pittsburgh, PA, USA
2 shared publications - Majd Sakr
Carnegie Mellon University, Pittsburgh, PA, USA
2 shared publications - Zipiao Wan
Carnegie Mellon University, Pittsburgh, PA, USA
2 shared publications
Latest Publications
- Open Access
- 14 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 1550-1551
Understanding the Role of Temperature in Diverse Question Generation by GPT-4
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.
- 14 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 1550-1551
Open AccessUnderstanding the Role of Temperature in Diverse Question Generation by GPT-4
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.
- Top Cited PapersOpen Access
- 29 January 2024
- Published by Association for Computing Machinery (ACM)
- p. 114-123
A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education
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.
- 29 January 2024
- Published by Association for Computing Machinery (ACM)
- p. 114-123
Top Cited PapersOpen AccessA Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education
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.
- 20 September 2021
- Published by Springer Nature
- p. 106-115
Semantic Influence Score: Tracing Beautiful Minds Through Knowledge Diffusion and Derivative Works
- 20 September 2021
- Published by Springer Nature
- p. 106-115
Semantic Influence Score: Tracing Beautiful Minds Through Knowledge Diffusion and Derivative Works