# Manipulating the Difficulty of C-Tests

arXiv: https://arxiv.org/abs/1906.06905 · HTML: https://mlsanity.com/paper/1906.06905/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2019.

## Built on by (most cited first, 5 of 5)

- [A quantitative study of NLP approaches to question difficulty estimation](https://mlsanity.com/paper/2305.10236/) (2023)
- [Annotation Curricula to Implicitly Train Non-Expert Annotators](https://mlsanity.com/paper/2106.02382/) (2021)
- [Constructing Open Cloze Tests Using Generation and Discrimination Capabilities of Transformers](https://mlsanity.com/paper/2204.07237/) (2022)
- [Controlling Cloze-test Question Item Difficulty with PLM-based Surrogate Models for IRT Assessment](https://mlsanity.com/paper/2403.01456/) (2024)
- [Constrained C-Test Generation via Mixed-Integer Programming](https://mlsanity.com/paper/2404.08821/) (2024)

## Abstract (arXiv)

We propose two novel manipulation strategies for increasing and decreasing the difficulty of C-tests automatically. This is a crucial step towards generating learner-adaptive exercises for self-directed language learning and preparing language assessment tests. To reach the desired difficulty level, we manipulate the size and the distribution of gaps based on absolute and relative gap difficulty predictions. We evaluate our approach in corpus-based experiments and in a user study with 60 participants. We find that both strategies are able to generate C-tests with the desired difficulty level.