Despite significant progress in the quality of language generated from
abstractive summarization models, these models still exhibit the tendency to
hallucinate, i.e., output content not supported by the source document. A
number of works have tried to fix--or at least uncover the source of--the
problem with limited success. In this paper, we identify a simple criterion
under which models are significantly more likely to assign more probability to
hallucinated content during generation: high model uncertainty. This finding
offers a potential explanation for hallucinations: models default to favoring
text with high marginal probability, i.e., high-frequency occurrences in the
training set, when uncertain about a continuation. It also motivates possible
routes for real-time intervention during decoding to prevent such
hallucinations. We propose a decoding strategy that switches to optimizing for
pointwise mutual information of the source and target token--rather than purely
the probability of the target token--when the model exhibits uncertainty.
Experiments on the XSum dataset show that our method decreases the probability
of hallucinated tokens while maintaining the Rouge and BertS scores of
top-performing decoding strategies.

本文发现了一个简单的标准 —— 模型不确定性高 —— 会导致生成更多的错误内容（即幻觉），并提出了一种解码策略，该策略在存在不确定性时优化源和目标单词的点间互信息，从而减少幻觉的出现，并在 XSum 数据集上进行了实验证明，该方法降低了幻觉的概率，同时保持了黄色和 BertS 得分。