LLMs predict forward reading, but fail to explain eye regressions
tallinzen · x · 2026-08-20
Research from NYU and UMass finds that while current language models can accurately predict the forward trajectory of human eye movements during reading, they fail to predict regressive saccades (jumping back) when a reader trips up. This reveals a gap in how LLMs model human reading cognition.
Related event: Language Models Predict Reading Progress but Fail to Explain Regressions(2 posts)→
More from Research
- 28.9M parameter LLM runs entirely on ESP32-S3 microcontroller — tom_doerr · 2026-08-20
- Multi-Agent Framework Evolves Rust Code That Reinvents Three Optimization Paradigms on an NP-Hard Problem — MonokoEloba · 2026-08-20
- Core robotics challenge: achieving one-shot generalization in the real world — Scobleizer · 2026-08-20
- Google DeepMind AI Restores Missing Words in 2,000-Year-Old Inscriptions — aftahi_ai · 2026-08-20
- Achira AI builds atomistic world models for AI to reason about and design chemistry — Tkaraletsos · 2026-08-20
- CZI virtual-cell program builds biological model stack — Tkaraletsos · 2026-08-20