France or Spain or Germany or France: A Neural Account of Non-Redundant Redundant Disjunctions
Not on the map. Why?
Abstract (arXiv)
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 an 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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 27 references that are in the map. First posted on arXiv 26 Feb 2026.
Builds on
12 of 27 references.
References · 12
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2022Locating and Editing Factual Associations in GPTcited by 2,609
- 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
- 2022Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 smallcited by 1,130
- 2022In-context Learning and Induction Headscited by 930
- 2023In-Context Learning Creates Task Vectorscited by 302
- 2023Function Vectors in Large Language Modelscited by 292
- 2023How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language modelcited by 199
- 2023Circuit Component Reuse Across Tasks in Transformer Language Modelscited by 105
- 2025How Linguistics Learned to Stop Worrying and Love the Language Modelscited by 50
- 2025The Dual-Route Model of Inductioncited by 22
Built on by
Not cited yet.