Aidan Doyle
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
Aidan Doyle has a total of 15 co-authors. Here are the top co-authors by number of 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 - Pragnya Sridhar
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.
- 7 June 2013
- Published by John Benjamins Publishing Company
- p. 345-372
Split intransitivity in Irish and the syntax-semantics interface
This paper considers the notion of split intransitivity as evidenced in the behaviour of perfects in Irish. It is claimed that this language exhibits a distinction between kinds of perfect which roughly corresponds to that between have and be perfects in other languages. However, the choice of perfect is initially somewhat puzzling, and a high degree of variability is found. In response to this, it is attempted to discover if the choice of perfect in Irish is dependent on such semantic factors as agentivity and telicity. The next part of the paper takes the Auxiliary Selection Hierarchy of Sorace (2000) and adapts it to the Irish data. Two semantic groups in particular are investigated: change-of-location verbs and change-of-state verbs. The findings of our examination strongly suggest that semantic factors play a major role in determining the kind of perfect chosen for intransitive verbs, but that one ought to think more in terms of trends in the behaviour of individual verbs, rather than absolute, unvarying rules. The paper tries to come to terms with a typologically unusual body of data. It is hoped that the analysis of this presented below will increase our understanding of the syntax-semantics interface as manifested in split intransitivity.
- 7 June 2013
- Published by John Benjamins Publishing Company
- p. 345-372
Split intransitivity in Irish and the syntax-semantics interface
This paper considers the notion of split intransitivity as evidenced in the behaviour of perfects in Irish. It is claimed that this language exhibits a distinction between kinds of perfect which roughly corresponds to that between have and be perfects in other languages. However, the choice of perfect is initially somewhat puzzling, and a high degree of variability is found. In response to this, it is attempted to discover if the choice of perfect in Irish is dependent on such semantic factors as agentivity and telicity. The next part of the paper takes the Auxiliary Selection Hierarchy of Sorace (2000) and adapts it to the Irish data. Two semantic groups in particular are investigated: change-of-location verbs and change-of-state verbs. The findings of our examination strongly suggest that semantic factors play a major role in determining the kind of perfect chosen for intransitive verbs, but that one ought to think more in terms of trends in the behaviour of individual verbs, rather than absolute, unvarying rules. The paper tries to come to terms with a typologically unusual body of data. It is hoped that the analysis of this presented below will increase our understanding of the syntax-semantics interface as manifested in split intransitivity.