France or Spain or Germany or France: A Neural Account of Non-Redundant Redundant Disjunctions
This research provides a neural explanation for how language models handle context-sensitive semantic interpretation, complementing existing symbolic analyses for linguists and NLP researchers.
The paper investigates the phenomenon of non-redundant redundant disjunctions in sentences like "France or Spain, or Germany or France." It demonstrates that large language models learn to bind contextually relevant information to repeated lexical items, and Transformer induction heads selectively attend to these context-licensed representations.
Sentences like "She will go to France or Spain, or perhaps to Germany or France." appear formally redundant, yet become acceptable in contexts such as "Mary will go to a philosophy program in France or Spain, or a mathematics program in Germany or France." While this phenomenon has typically been analyzed using symbolic formal representations, we aim to provide a complementary account grounded in artificial neural mechanisms. We first present new behavioral evidence from humans and large language models demonstrating the robustness of this apparent non-redundancy across contexts. We then show that, in language models, redundancy avoidance arises from two interacting mechanisms: models learn to bind contextually relevant information to repeated lexical items, and Transformer induction heads selectively attend to these context-licensed representations. We argue that this neural explanation sheds light on the mechanisms underlying context-sensitive semantic interpretation, and that it complements existing symbolic analyses.