改进的束搜索用于抽象摘要中的幻觉缓解
Improved Beam Search for Hallucination Mitigation in Abstractive Summarization
AI总结：
本文提出一种NLI辅助的束重排序机制，利用蕴含概率分数检测并预防摘要生成中的幻觉，在XSum和CNN/DM数据集上显著优于普通束搜索。
摘要：
大型预训练语言模型的进步显著提升了它们在包括摘要生成在内的条件语言生成任务上的性能，尽管存在幻觉问题。为减少幻觉，传统方法提出改进束搜索或使用事实检查器作为后处理步骤。在本文中，我们研究了利用自然语言推理（NLI）蕴含度量来检测和预防摘要生成中的幻觉。我们提出了一种NLI辅助的束重排序机制，通过在显著性增强的贪心解码过程中计算输入上下文与摘要生成模型生成的束之间的蕴含概率分数来实现。此外，引入了一个多样性度量来与普通束搜索进行有效性比较。我们提出的算法在XSum和CNN/DM数据集上显著优于普通束解码。
英文摘要：
Advancement in large pretrained language models has significantly improved their performance for conditional language generation tasks including summarization albeit with hallucinations. To reduce hallucinations, conventional methods proposed improving beam search or using a fact checker as a postprocessing step. In this paper, we investigate the use of the Natural Language Inference (NLI) entailment metric to detect and prevent hallucinations in summary generation. We propose an NLI-assisted beam re-ranking mechanism by computing entailment probability scores between the input context and summarization model-generated beams during saliency-enhanced greedy decoding. Moreover, a diversity metric is introduced to compare its effectiveness against vanilla beam search. Our proposed algorithm significantly outperforms vanilla beam decoding on XSum and CNN/DM datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
