pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2023 1

verdicts

CONDITIONAL 1

representative citing papers

The Internal State of an LLM Knows When It's Lying

cs.CL · 2023-04-26 · conditional · novelty 6.0

Hidden activations in LLMs encode detectable information about statement truthfulness, enabling a classifier to identify true versus false content more reliably than the model's assigned probabilities.

citing papers explorer

Showing 1 of 1 citing paper.

  • The Internal State of an LLM Knows When It's Lying cs.CL · 2023-04-26 · conditional · none · ref 21

    Hidden activations in LLMs encode detectable information about statement truthfulness, enabling a classifier to identify true versus false content more reliably than the model's assigned probabilities.