Exploring Cognitively Informed Sentence Simplification with Gaze-Guided Text Generation

Andreas Säuberli, Diego Frassinelli, Barbara Plank


Abstract
Automatic text simplification has mostly relied on human judgments when it comes to what is considered easy or difficult to read. Eye movements while reading can offer a more direct and objective signal of processing effort and reading ease. In this paper, we explore gaze-guided text generation (GGTG), an approach to control reading ease in generated texts, and assess its use for sentence simplification. GGTG employs a gaze model that is trained to predict eye-tracking measures such as reading times or regression rates, which are then used to rerank next-token probabilities generated by a language model. We evaluated the approach on an English sentence simplification benchmark and found gains in automatic evaluation metrics, although the simplification operations are mostly limited to the lexical level. Its modular nature also allows GGTG to be combined with other simplification techniques such as prompting or fine-tuning.
Anthology ID:
2026.gaze4nlp-1.3
Volume:
Proceedings fo the Second International Workshop on Eye-Tracking Resources and Evaluation for Human-Aligned NLP
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Cengiz Acartürk, Burcu Can, Jamal Nasir, Çağrı Çöltekin
Venues:
Gaze4NLP | WS
SIG:
Publisher:
ELDA
Note:
Pages:
16–23
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-gaze4nlp-03
DOI:
10.63317/3cju9gvduaga
Bibkey:
Cite (ACL):
Andreas Säuberli, Diego Frassinelli, and Barbara Plank. 2026. Exploring Cognitively Informed Sentence Simplification with Gaze-Guided Text Generation. In Proceedings fo the Second International Workshop on Eye-Tracking Resources and Evaluation for Human-Aligned NLP, pages 16–23, Palma de Mallorca, Spain. ELDA.
Cite (Informal):
Exploring Cognitively Informed Sentence Simplification with Gaze-Guided Text Generation (Säuberli et al., Gaze4NLP 2026)
Copy Citation: