pith. sign in

Title resolution pending

3 Pith papers cite this work. Polarity classification is still indexing.

3 Pith papers citing it

fields

cs.CL 2 cs.CV 1

years

2023 3

clear filters

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.

Baichuan 2: Open Large-scale Language Models

cs.CL · 2023-09-19 · unverdicted · novelty 4.0

Baichuan 2 presents 7B and 13B LLMs trained on 2.6T tokens that match or exceed similar open models on MMLU, CMMLU, GSM8K, HumanEval and excel in medicine and law.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • The Internal State of an LLM Knows When It's Lying cs.CL · 2023-04-26 · conditional · none · ref 32

    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.