Recent developments in the use of large-language models have led to substantial improvements in the accuracy of content-based automated scoring of free-text responses. The reported accuracy levels suggest that automated systems could have widespread applicability in assessment. However, before they are used in operational testing, other aspects of…

RobotReviewer is a tool for automatically assessing the risk of bias in randomized controlled trials, but there is limited evidence of its reliability. We evaluated the agreement between RobotReviewer and humans regarding the risk of bias assessment based on 1955 randomized controlled trials. The risk of bias in these trials was assessed via two…

Systematic reviews are vital for guiding practice, research and policy, although they are often slow and labour-intensive. Large language models (LLMs) could speed up and automate systematic reviews, but their performance in such tasks has yet to be comprehensively evaluated against humans, and no study has tested Generative Pre-Trained…

Background: Generative artificial intelligence (AI) represents a potentially powerful, time-saving tool for grading student essays. However, little is known about how AI-generated essay scores compare to human instructor scores. Objective: The purpose of this study was to compare the essay grading scores produced by AI with those of human…

AI-enabled assessment of student papers has the potential to provide both summative and formative feedback and reduce the time spent on grading. Using auto-ethnography, this study compares AI-enabled and human assessment of business student examination papers in a law module based on previously established rubrics. Examination papers were…

We study how to automatically generate cloze questions from given texts to assess reading comprehension, where a cloze question consists of a stem with a blank space holder for the answer key, and three distractors for generating confusions. We present a generative method called CQG (Cloze Question Generator) for constructing cloze questions from…

As the development and application of large language models (LLMs) in physics education progress, the well-known AI-based chatbot ChatGPT4 has presented numerous opportunities for educational assessment. Investigating the potential of AI tools in practical educational assessment carries profound significance. This study explored the comparative…

Argumentation, a key scientific practice presented in the "Framework for K-12 Science Education," requires students to construct and critique arguments, but timely evaluation of arguments in large-scale classrooms is challenging. Recent work has shown the potential of automated scoring systems for open response assessments, leveraging…

Background: Multiple-choice item (MCI) assessments are burdensome for instructors to develop. Artificial intelligence (AI, e.g., ChatGPT) can streamline the process without sacrificing quality. The quality of AI-generated MCIs and human experts is comparable. However, whether the quality of AI-generated MCIs is equally good across various domain-…

This study investigates the validity and reliability of generative large language models (LLMs), specifically ChatGPT and Google's Bard, in grading student essays in higher education based on an analytical grading rubric. A total of 15 experienced English as a foreign language (EFL) instructors and two LLMs were asked to evaluate three student…

Broadly defined, academic language (AL) is a set of lexical-grammatical norms and registers commonly used in educational and academic discourse. Mastery of academic language in writing is an important aspect of writing instruction and assessment. The purpose of this study was to use Natural Language Processing (NLP) tools to examine the extent to…

Manually scoring and revising student essays has long been a time-consuming task for educators. With the rise of natural language processing techniques, automated essay scoring (AES) and automated essay revising (AER) have emerged to alleviate this burden. However, current AES and AER models require large amounts of training data and lack…

In a randomized trial that collects text as an outcome, traditional approaches for assessing treatment impact require that each document first be manually coded for constructs of interest by human raters. An impact analysis can then be conducted to compare treatment and control groups, using the hand-coded scores as a measured outcome. This…

With the rapid development of generative artificial intelligence (AI) frameworks (e.g., the generative pre-trained transformer [GPT]), a growing number of researchers have started to explore its potential as an automated essay scoring (AES) system. While previous studies have investigated the alignment between human ratings and GPT ratings, few…

This study conducts a comprehensive quantitative evaluation of OpenAI's language model, ChatGPT 4, for grading Task 2 writing of the IELTS exam. The objective is to assess the alignment between ChatGPT's grading and that of official human raters. The analysis encompassed a multifaceted approach, including a comparison of means and reliability…