A symbol-remapping benchmark shows that LLMs' arithmetic and symbolic reasoning accuracy drops sharply when familiar digits and operators are replaced, revealing heavy reliance on memorized tokens rather than abstract rules.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective
A symbol-remapping benchmark shows that LLMs' arithmetic and symbolic reasoning accuracy drops sharply when familiar digits and operators are replaced, revealing heavy reliance on memorized tokens rather than abstract rules.