Controlling Reading Ease with Gaze-Guided Text Generation

2026-01-25

AI Summary

This work proposes a controllable text generation method guided by eye-movement-based cognitive signals to dynamically adjust textual difficulty according to individual readers’ linguistic proficiency and cognitive load. By integrating an eye-movement prediction model—trained on human reading behavior—with a language model, the system modulates lexical complexity in generated text, achieving the first interpretable and cognitively informed approach to difficulty-controlled generation. Experimental results demonstrate that the method significantly influences both reading time and subjective difficulty ratings among both native and non-native English speakers, confirming its effectiveness and cross-linguistic applicability.

Technology Category

• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Computer Vision: Language and Vision

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The way our eyes move while reading can tell us about the cognitive effort required to process the text. In the present study, we use this fact to generate texts with controllable reading ease. Our method employs a model that predicts human gaze patterns to steer language model outputs towards eliciting certain reading behaviors. We evaluate the approach in an eye-tracking experiment with native and non-native speakers of English. The results demonstrate that the method is effective at making the generated texts easier or harder to read, measured both in terms of reading times and perceived difficulty of the texts. A statistical analysis reveals that the changes in reading behavior are mostly due to features that affect lexical processing. Possible applications of our approach include text simplification for information accessibility and generation of personalized educational material for language learning.

Problem

• reading ease
• text generation
• gaze prediction
• lexical processing
• text simplification

Innovation

• gaze-guided generation
• reading ease control
• eye-tracking
• text simplification
• language model steering