44 citations · 141 across the 13 of their papers we have counts for
13 papers
Understanding the Role of Temperature in Diverse Question Generation by GPT-4
Arav Agarwal, Karthik Mittal, Aidan Doyle +5
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 sign…
From GPT-3 to GPT-4: On the Evolving Efficacy of LLMs to Answer Multiple-choice Questions for Programming Classes in Higher Education
Jaromir Savelka, Arav Agarwal, Christopher Bogart +1
We explore the evolving efficacy of three generative pre-trained transformer (GPT) models in generating answers for multiple-choice questions (MCQ) from introductory and intermedia…
From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems
Samyar Janatian, Hannes Westermann, Jinzhe Tan +2
Encoding legislative text in a formal representation is an important prerequisite to different tasks in the field of AI & Law. For example, rule-based expert systems focused on leg…
Efficient Classification of Student Help Requests in Programming Courses Using Large Language Models
Jaromir Savelka, Paul Denny, Mark Liffiton +1
The accurate classification of student help requests with respect to the type of help being sought can enable the tailoring of effective responses. Automatically classifying such r…
Using Large Language Models to Support Thematic Analysis in Empirical Legal Studies
Jakub Drápal, Hannes Westermann, Jaromir Savelka
Thematic analysis and other variants of inductive coding are widely used qualitative analytic methods within empirical legal studies (ELS). We propose a novel framework facilitatin…
CodeHelp: Using Large Language Models with Guardrails for Scalable Support in Programming Classes
Mark Liffiton, Brad Sheese, Jaromir Savelka +1
Computing educators face significant challenges in providing timely support to students, especially in large class settings. Large language models (LLMs) have emerged recently and…