Workshop on the Linguistic Principles for Foundation Models

The meeting examines how wording, natural languages, code and formal notation influence foundation-model performance. Linguistic concepts such as compositionality, ambiguity, tokenization and pragmatics provide a basis for studying changes in reasoning, internal representation, generalization and alignment. Session: 08:00–17:00 (Australia/Sydney). A paid NeurIPS virtual pass includes workshop livestreams; on-site access follows the host-location registration rules.