English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Developing an educational test can be expensive and time-consuming, as eachitem must be written by experts and then evaluated by collecting hundreds ofstudent responses. Moreover, many tests require multiple distinct sets ofquestions administered throughout the school year to closely monitor students'progress, known as parallel tests. In this study, we focus on tests of silentsentence reading efficiency, used to assess students' reading ability overtime. To generate high-quality parallel tests, we propose to fine-tune largelanguage models (LLMs) to simulate how previous students would have respondedto unseen items. With these simulated responses, we can estimate each item'sdifficulty and ambiguity. We first use GPT-4 to generate new test itemsfollowing a list of expert-developed rules and then apply a fine-tuned LLM tofilter the items based on criteria from psychological measurements. We alsopropose an optimal-transport-inspired technique for generating parallel testsand show the generated tests closely correspond to the original test'sdifficulty and reliability based on crowdworker responses. Our evaluation of agenerated test with 234 students from grades 2 to 8 produces test scores highlycorrelated (r=0.93) to those of a standard test form written by human expertsand evaluated across thousands of K-12 students.

Generating and Evaluating Tests for K-12 Students with Language Model Simulations: A Case Study on Sentence Reading Efficiency