Is it Possible to Modify Text to a Target Readability Level? An Initial Investigation Using Zero-Shot Large Language Models
This addresses the need for customizable text complexity for diverse audiences, but it is incremental as it builds on existing text modification tasks.
The paper tackles the problem of directly modifying text to an absolute target readability level, proposing a new task with 8 versions per input, and finds that zero-shot LLMs can adjust readability directionally but final levels remain correlated with the source text, with semantic similarity dropping by up to 0.2 for large shifts.
Text simplification is a common task where the text is adapted to make it easier to understand. Similarly, text elaboration can make a passage more sophisticated, offering a method to control the complexity of reading comprehension tests. However, text simplification and elaboration tasks are limited to only relatively alter the readability of texts. It is useful to directly modify the readability of any text to an absolute target readability level to cater to a diverse audience. Ideally, the readability of readability-controlled generated text should be independent of the source text. Therefore, we propose a novel readability-controlled text modification task. The task requires the generation of 8 versions at various target readability levels for each input text. We introduce novel readability-controlled text modification metrics. The baselines for this task use ChatGPT and Llama-2, with an extension approach introducing a two-step process (generating paraphrases by passing through the language model twice). The zero-shot approaches are able to push the readability of the paraphrases in the desired direction but the final readability remains correlated with the original text's readability. We also find greater drops in semantic and lexical similarity between the source and target texts with greater shifts in the readability.