Language models contain small neuron subsets whose suppression degrades factuality performance, interpreted by the authors as 'truth neurons'.
Dola: Decoding by contrasting layers improves factuality in large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Truth Neurons
Language models contain small neuron subsets whose suppression degrades factuality performance, interpreted by the authors as 'truth neurons'.