Controlled experiments show implicit multi-hop reasoning in LLMs requires prior exposure to compositional contexts during pretraining and does not transfer to unexposed individuals.
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models , url =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.