AI RESEARCH
Algorithmic Consequences of Particle Filters for Sentence Processing: Amplified Garden-Paths and Digging-In Effects
arXiv CS.CL
•
ArXi:2603.11412v1 Announce Type: new Under surprisal theory, linguistic representations affect processing difficulty only through the bottleneck of surprisal. Our best estimates of surprisal come from large language models, which have no explicit representation of structural ambiguity. While LLM surprisal robustly predicts reading times across languages, it systematically underpredicts difficulty when structural expectations are violated -- suggesting that representations of ambiguity are causally implicated in sentence processing.