Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey
Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey
复制标题
DOI：
10.48550/arxiv.2311.07914
复制
发表时间：
2023-11
期刊：
影响因子：
--
通讯作者：
Garima Agrawal;Tharindu Kumarage;Zeyad Alghami;Huanmin Liu
中科院分区：
文献类型：
--
作者：
Garima Agrawal;Tharindu Kumarage;Zeyad Alghami;Huanmin Liu
当代的LLM容易产生幻觉，主要源于模型中的知识空白。为了解决这一关键限制，研究人员采用了不同的策略，通过结合外部知识来增强LLMS，旨在减少幻觉并提高推理准确性。在这些战略中，利用知识图谱作为外部信息来源显示了令人振奋的成果。在这项调查中，我们全面回顾了这些基于知识图的LLMS增强技术，重点讨论了它们在减轻幻觉方面的有效性。我们系统地将这些方法分为三个主要组，提供方法学比较和性能评估。最后，这项调查探讨了与这些技术相关的当前趋势和挑战，并概述了这一新兴领域未来研究的潜在途径。
The contemporary LLMs are prone to producing hallucinations, stemming mainly from the knowledge gaps within the models. To address this critical limitation, researchers employ diverse strategies to augment the LLMs by incorporating external knowledge, aiming to reduce hallucinations and enhance reasoning accuracy. Among these strategies, leveraging knowledge graphs as a source of external information has demonstrated promising results. In this survey, we comprehensively review these knowledge-graph-based augmentation techniques in LLMs, focusing on their efficacy in mitigating hallucinations. We systematically categorize these methods into three overarching groups, offering methodological comparisons and performance evaluations. Lastly, this survey explores the current trends and challenges associated with these techniques and outlines potential avenues for future research in this emerging field.