AI RESEARCH
Repetition Without Exclusivity: Scale Sensitivity of Referential Mechanisms in Child-Scale Language Models
arXiv CS.LG
•
ArXi:2603.13696v1 Announce Type: cross We present the first systematic evaluation of mutual exclusivity (ME) -- the bias to map novel words to novel referents -- in text-only language models trained on child-directed speech. We operationalise ME as referential suppression: when a familiar object is relabelled in a two-referent dis