LLMs rely on rote memorization for an average of 19.6% of knowledge points on MMLU and GSM8K, revealed by reformulating MCQs into a knowledge-centric trinity format that reduces memorization effects while preserving core knowledge.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Large Language Models Could Be Rote Learners
LLMs rely on rote memorization for an average of 19.6% of knowledge points on MMLU and GSM8K, revealed by reformulating MCQs into a knowledge-centric trinity format that reduces memorization effects while preserving core knowledge.