从幻觉到事实：利用精选知识图谱增强语言模型
From Hallucinations to Facts: Enhancing Language Models with Curated Knowledge Graphs
AI总结：
本文提出通过整合从维基百科构建并精炼的精选知识图谱三元组来增强语言模型的事实依据，实验证明该方法能有效减少幻觉回答，提升模型输出的可靠性与可信度。
摘要：
幻觉是长期困扰语言模型的一项挑战，它通过生成偏离事实准确性或连贯性的回答，削弱了模型在各种自然语言处理任务中的有效性与可信度。本文通过整合精选的知识图谱（KG）三元组，将回答锚定在经验数据之上，以解决语言模型的幻觉问题。我们精心挑选并整合针对特定语境的相关知识图谱三元组，从而增强事实依据以及与输入的对齐程度。我们的贡献包括从维基百科构建一个全面的知识图谱存储库，并对数据进行精炼，以突出对模型训练至关重要的信息。通过让语言模型能够访问这些经过整理的知识，我们旨在生成既语言流畅、又深深植根于事实准确性和语境相关性的回答。这种整合通过提供坚实的信息基础来减轻幻觉，使模型能够在生成回答期间利用丰富的事实数据储备。实验评估证明了多种方法在减少幻觉性回答方面的有效性，凸显了精选知识图谱在提升语言模型输出的可靠性与可信度方面的作用。
英文摘要：
Hallucination, a persistent challenge plaguing language models, undermines their efficacy and trustworthiness in various natural language processing endeavors by generating responses that deviate from factual accuracy or coherence. This paper addresses language model hallucination by integrating curated knowledge graph (KG) triples to anchor responses in empirical data. We meticulously select and integrate relevant KG triples tailored to specific contexts, enhancing factual grounding and alignment with input. Our contribution involves constructing a comprehensive KG repository from Wikipedia and refining data to spotlight essential information for model training. By imbuing language models with access to this curated knowledge, we aim to generate both linguistically fluent responses and deeply rooted in factual accuracy and context relevance. This integration mitigates hallucinations by providing a robust foundation of information, enabling models to draw upon a rich reservoir of factual data during response generation. Experimental evaluations demonstrate the effectiveness of multiple approaches in reducing hallucinatory responses, underscoring the role of curated knowledge graphs in improving the reliability and trustworthiness of language model outputs.
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。
