In authors or contributors

1 resource

  • Amos Azaria, Tom Mitchell
    |
    Oct 17th, 2023
    |
    preprint
    Amos Azaria, Tom Mitchell
    Oct 17th, 2023

    While Large Language Models (LLMs) have shown exceptional performance in various tasks, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone. In this paper, we provide evidence that the LLM's internal state can be used to reveal the truthfulness of statements. This includes both statements provided to the LLM, and statements that the LLM itself generates. Our approach is to train a classifier that outputs the probability that a statement...

Last update from database: 05/02/2025, 20:15 (UTC)
Powered by Zotero and Kerko.