We study how to characterize and predict the truthfulness of texts generated
from large language models (LLMs), which serves as a crucial step in building
trust between humans and LLMs. Although several approaches based on entropy or
verbalized uncertainty have been proposed to calibrate model predictions, these
methods are often intractable, sensitive to hyperparameters, and less reliable
when applied in generative tasks with LLMs. In this paper, we suggest
investigating internal activations and quantifying LLM's truthfulness using the
local intrinsic dimension (LID) of model activations. Through experiments on
four question answering (QA) datasets, we demonstrate the effectiveness
othis https URL our proposed method. Additionally,
we study intrinsic dimensions in LLMs and their relations with model layers,
autoregressive language modeling, and the training of LLMs, revealing that
intrinsic dimensions can be a powerful approach to understanding LLMs.

我们研究了如何表征和预测由大型语言模型生成的文本的真实性，这在人类与语言模型之间建立信任的过程中起着关键作用。通过对四个问答数据集进行实验，我们提出的方法通过研究内部激活和量化语言模型激活的本地内在维度（LID）来证明其有效性。此外，我们还研究了语言模型中的内在维度及其与模型层、自回归语言建模和语言模型训练的关系，揭示了内在维度在理解语言模型中的潜力。