Decoding Open-Ended Information Seeking Goals from Eye Movements in Reading
Cfir Avraham Hadar, Omer Shubi, Yoav Meiri, Yevgeni Berzak
2025-05-07
Summary
This paper talks about how AI models can figure out what someone is looking for while reading, just by analyzing their eye movements.
What's the problem?
It's hard to know exactly what a person wants to find or learn when they're reading, because people don't always say their goals out loud, and traditional methods can't easily guess their intentions.
What's the solution?
The researchers showed that by studying the way people's eyes move across a page, AI can accurately guess what kind of information the reader is searching for and even reconstruct their specific goals.
Why it matters?
This matters because it could make reading and learning tools much smarter, helping websites, apps, or e-books adapt to what a person needs, making studying and searching for information more personalized and efficient.
Abstract
LLMs can ascertain readers' specific information goals through eye movement data, as demonstrated by successful goal classification and reconstruction tasks.