Pairing questions and adding distractor options reliably lowers LLM scores across three benchmarks, and the authors use this to create a harder 'resurrected' version of MMLU.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Resurrecting saturated LLM benchmarks with adversarial encoding
Pairing questions and adding distractor options reliably lowers LLM scores across three benchmarks, and the authors use this to create a harder 'resurrected' version of MMLU.