A linear probe on frozen LLM activations comes within 0.6 to 2.1 accuracy points of fine-tuned ESG classifiers, and beats the model's own answer in eleven of twelve comparisons.
, Holzm \"u ller, D
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes
A linear probe on frozen LLM activations comes within 0.6 to 2.1 accuracy points of fine-tuned ESG classifiers, and beats the model's own answer in eleven of twelve comparisons.