Search papers, labs, and topics across Lattice.
This study investigates the distinct processing dynamics of conceptual and referential disruptions during reading in humans and large language models (LLMs). Using self-paced reading and model prediction analysis, it reveals that conceptual disruptions lead to immediate and localized processing costs, while referential disruptions result in weaker, more gradual effects influenced by sentence boundaries. The findings highlight that conceptual information incurs a concentrated integration cost, whereas referential information engages a more distributed maintenance process, providing insights into the cognitive and computational mechanisms of meaning processing.
Conceptual disruptions in reading trigger immediate, localized processing costs, while referential disruptions unfold gradually, revealing fundamental differences in how meaning is processed by humans and LLMs.
Linguistic meaning is grounded in conceptual content, from which reference to particular entities emerges as words enter discourse. To examine the processing dynamics associated with these two dimensions of meaning, we selectively disrupted conceptual or referential information in short narratives and traced the resulting effects in human self-paced reading and in the predictive and representational processing of large language models. In human reading, conceptual disruptions produced a strong but localized processing cost, emerging immediately after the distorted word, reaching an early maximum, and then declining rapidly. Referential disruptions produced weaker effects, which decreased more gradually across subsequent words, and were more strongly modulated by sentence boundaries. In the language model, both disruptions emerged immediately at the manipulated word. Contextual model surprisal showed a pattern closely paralleling human reading: conceptual disruption produced a larger, more locally concentrated effect that decayed rapidly, whereas referential disruption produced a smaller and more gradual downstream effect. Output-layer representations showed a different pattern: referential disruption produced a larger initial displacement, while both distortions were subsequently characterized by power-law decay. Together, these results provide convergent evidence for distinguishable processing dynamics of two types of meaning: conceptual information imposes a more locally concentrated integration cost, whereas referential information engages a more distributed process of maintaining discourse-level identity.
