Keren Gruteke-Klein

Automatic methods for scoring text readability have been studied for over a century, and are widely used in research and in user-facing applications in many domains. Thus far, the development and evaluation of such methods have primarily relied on two types of offline human behavioral data, performance on reading comprehension tests and ratings of text readability levels. In this work, we instead focus on a fundamental and understudied aspect of readability, real-time reading ease, captured with online reading measures using eye tracking. We introduce a new cognitive evaluation framework for readability scoring methods that quantifies their ability to account for reading ease, while controlling for content variation across texts. Applying this evaluation to prominent traditional readability formulas, NLP-based methods, commercial systems used in education, and frontier LLMs suggests that they are all poor predictors of English reading ease in adults as compared to word properties commonly used in psycholinguistics for the prediction of reading times. This outcome holds across L1 and L2 speakers, different reading regimes, and textual units of different lengths. Our results reveal an important limitation of a wide range of methods for readability scoring, highlight the utility of real-time behavioral benchmarks for readability research, and call for new, cognitively driven readability scoring approaches that can better account for how humans experience texts in real time.

We present EyeBench, the first benchmark designed to evaluate machine learning models that decode cognitive and linguistic information from eye movements during reading. EyeBench offers an accessible entry point to the challenging and underexplored domain of modeling eye tracking data paired with text, aiming to foster innovation at the intersection of multimodal AI and cognitive science. The benchmark provides a standardized evaluation framework for predictive models, covering a diverse set of datasets and tasks, ranging from assessment of reading comprehension to detection of developmental dyslexia. Progress on the EyeBench challenge will pave the way for both practical real-world applications, such as adaptive user interfaces and personalized education, and scientific advances in understanding human language processing. The benchmark is released as an open-source software package which includes data downloading and harmonization scripts, baselines and state-of-the-art models, as well as evaluation code, publicly available at https://github.com/EyeBench/eyebench.

Text simplification is a common practice for making texts easier to read and easier to understand. To which extent does it achieve these goals, and which participant and text characteristics drive simplification benefits? In this work, we use eye tracking to address these questions for the first time for the population of adult native (L1) English speakers. We find that 42% of the readers exhibit reading facilitation effects, while only 2% improve reading comprehension accuracy. We further observe that reading fluency benefits are larger for slower and less experienced readers, while comprehension benefits are more substantial in lower comprehension readers, but not vice versa. Finally, we find that high-complexity original texts are key for enhancing reading fluency, while large complexity reduction is more pertinent to improving comprehension. Our study highlights the potential of cognitive measures in the evaluation of text simplification and distills empirically driven principles for enhancing simplification effectiveness.

The effect of surprisal on processing difficulty has been a central topic of investigation in psycholinguistics. Here, we use eyetracking data to examine three language processing regimes that are common in daily life but have not been addressed with respect to this question: information seeking, repeated processing, and the combination of the two. Using standard regime-agnostic surprisal estimates we find that the prediction of surprisal theory regarding the presence of a linear effect of surprisal on processing times, extends to these regimes. However, when using surprisal estimates from regime-specific contexts that match the contexts and tasks given to humans, we find that in information seeking, such estimates do not improve the predictive power of processing times compared to standard surprisals. Further, regime-specific contexts yield near zero surprisal estimates with no predictive power for processing times in repeated reading. These findings point to misalignments of task and memory representations between humans and current language models, and question the extent to which such models can be used for estimating cognitively relevant quantities. We further discuss theoretical challenges posed by these results.