Frozen LLMs reach near-perfect accuracy on several abstract reasoning benchmarks after tuning only the token embedding layer, implying poor zero-shot scores reflect input mismatch rather than absent reasoning.
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
-
What is an "Abstract Reasoner"? Revisiting Experiments and Arguments about Large Language Models
Frozen LLMs reach near-perfect accuracy on several abstract reasoning benchmarks after tuning only the token embedding layer, implying poor zero-shot scores reflect input mismatch rather than absent reasoning.