Large Language Models (LLMs) are adept at text manipulation -- tasks such as machine translation and text summarization. However, these models can also be prone to hallucination, which can be detrimental to the faithfulness of any answers that the model provides. Recent works in combating hallucinations in LLMs deal with identifying hallucinated sentences and categorizing the different ways in which models hallucinate. This paper takes a deep dive into LLM behavior with respect to hallucinations, defines a token-level approach to identifying different kinds of hallucinations, and further utilizes this token-level tagging to improve the interpretability and faithfulness of LLMs in dialogue summarization tasks. Through this, the paper presents a new, enhanced dataset and a new training paradigm.

翻译：大语言模型（LLMs）擅长文本操作——例如机器翻译和文本摘要等任务。然而，这些模型也容易产生幻觉，这可能损害模型所提供任何答案的忠实性。近期对抗大语言模型中幻觉的研究主要涉及识别存在幻觉的句子以及分类模型产生幻觉的不同方式。本文深入探究了大语言模型在幻觉方面的行为，定义了识别不同类型幻觉的令牌级方法，并进一步利用这种令牌级标记来提升大语言模型在对话摘要任务中的可解释性和忠实性。通过这项工作，本文提出了一个新的增强型数据集和一种新的训练范式。