Pith. sign in

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 1

years

2025 1

verdicts

REJECT 1

roles

background 1

polarities

unclear 1

representative citing papers

Truth Neurons

cs.CL · 2025-05-18 · reject · novelty 5.0

Language models contain small neuron subsets whose suppression degrades factuality performance, interpreted by the authors as 'truth neurons'.

citing papers explorer

Showing 1 of 1 citing paper.

  • Truth Neurons cs.CL · 2025-05-18 · reject · none · ref 8

    Language models contain small neuron subsets whose suppression degrades factuality performance, interpreted by the authors as 'truth neurons'.