Two-hop reasoning fails when the second hop is out-of-distribution because upper layers of a transformer are trained to map already-formed representations to outputs rather than reason over them, and a looped architecture that aligns representations with inputs substantially recovers the ability.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models
Two-hop reasoning fails when the second hop is out-of-distribution because upper layers of a transformer are trained to map already-formed representations to outputs rather than reason over them, and a looped architecture that aligns representations with inputs substantially recovers the ability.