Controlled experiments show implicit multi-hop reasoning in LLMs requires prior exposure to compositional contexts during pretraining and does not transfer to unexposed individuals.
Do large language models have compositional ability? an investigation into limitations and scalability
2 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
2
Pith papers citing it
1
external citations · external index
representative citing papers
A procedurally generated benchmark decomposes spatial-reasoning tests into four compositional axes and shows LLMs degrade sharply with reasoning depth.
citing papers explorer
-
Multi-Hop Knowledge Composition is Bound by Pretraining Exposure
Controlled experiments show implicit multi-hop reasoning in LLMs requires prior exposure to compositional contexts during pretraining and does not transfer to unexposed individuals.
-
DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning
A procedurally generated benchmark decomposes spatial-reasoning tests into four compositional axes and shows LLMs degrade sharply with reasoning depth.