LLMs encode multiple dataset-specific linear directions in their hidden states that predict their own answer correctness, and these directions are nearly independent across benchmarks.
QAMPARI : A benchmark for open-domain questions with many answers
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
-
Pretrained LLMs Learn Multiple Types of Uncertainty
LLMs encode multiple dataset-specific linear directions in their hidden states that predict their own answer correctness, and these directions are nearly independent across benchmarks.