RHO（$\ ho$）：利用知识接地减少开放域对话中的幻觉
RHO ($ρ$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding
AI总结：
本文提出RHO模型，通过局部和全局知识接地结合知识图谱嵌入，并设计基于子图游走的重排序，显著减少开放域对话中的幻觉，在OpenDialKG上大幅超越现有方法。
摘要：
对话系统可以利用大型预训练语言模型和知识来生成流畅且信息丰富的响应。然而，这些模型仍然容易产生不受输入源支持的幻觉响应，这极大地阻碍了它们的应用。外部知识与对话上下文之间的异质性对表示学习和源整合提出了挑战，并进一步导致不忠实。为了应对这一挑战并生成更忠实的响应，本文提出了RHO（$\ ho$），利用知识图谱（KG）中链接实体和关系谓词的表示。我们提出了（1）局部知识接地，将文本嵌入与相应的KG嵌入相结合；（2）全局知识接地，通过注意力机制赋予RHO多跳推理能力。此外，我们设计了一种基于KG子图游走的响应重排序技术，以更好地进行对话推理。在OpenDialKG上的实验结果表明，我们的方法在自动评估和人工评估上均大幅优于最先进的方法，尤其是在幻觉减少方面（FeQA中降低17.54%）。
英文摘要：
Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses. However, these models are still prone to produce hallucinated responses not supported by the input source, which greatly hinders their application. The heterogeneity between external knowledge and dialogue context challenges representation learning and source integration, and further contributes to unfaithfulness. To handle this challenge and generate more faithful responses, this paper presents RHO ($ρ$) utilizing the representations of linked entities and relation predicates from a knowledge graph (KG). We propose (1) local knowledge grounding to combine textual embeddings with the corresponding KG embeddings; and (2) global knowledge grounding to equip RHO with multi-hop reasoning abilities via the attention mechanism. In addition, we devise a response re-ranking technique based on walks over KG sub-graphs for better conversational reasoning. Experimental results on OpenDialKG show that our approach significantly outperforms state-of-the-art methods on both automatic and human evaluation by a large margin, especially in hallucination reduction (17.54% in FeQA).
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。
