Two papers on text simplification accepted at LREC 2026 and the Gaze4NLP workshop

“Evaluating LLM-Based Text Simplification for German: Effects on Post-Editing Effort, Quality Ratings, and User Comprehension” (led by Luisa Carrer)

• We conducted comprehensive human evaluation studies to measure the real-world impact of LLMs for German text simplification.
• We involved post-editors, experts, as well as end-users with and without cognitive impairments, collecting both quantitative and qualitative data.
• Results show that LLM-based text simplification can improve post-editing productivity as well as end-user comprehension and perception.

The paper was accepted for an oral presentation at the Fifteenth Language Resources and Evaluation Conference (LREC) in Palma (Mallorca, Spain) on May 11-16.

“Exploring Cognitively Informed Sentence Simplification with Gaze-Guided Text Generation”

• We applied gaze-guided text generation to simplify English sentences based on eye-tracking data.
• Automatic evaluation shows that improvements in readability can be achieved using this approach.
• The approach can be combined with prompting, fine-tuning, or other simplification strategies.

The paper was accepted for an oral presentation at the Second International Workshop on Eye-Tracking Resources and Evaluation for Human-Aligned NLP (Gaze4NLP) at LREC in Palma (Mallorca, Spain) on May 12, 2026.