基于知识图的检索增强生成 (RAG) 模型的构建和应用的研究
Sili Wang1,2, Heng Yang3,4, Wei Liu3,4
1Key Laboratory of Ecological Safety and Sustainable Development in Arid Lands, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, 730000, China. wangsl@llas.ac.cn.
Scientific reports
|November 18, 2025
概括
本研究介绍了一种基于知识图的检索增强生成模型 (KG-RAG),用于对抗人工智能中的事实幻觉. 通过整合知识图表,KG-RAG增强了生成模型,提高了问题回答中的事实准确性和知识及时性.
科学领域:
- 人工智能的人工智能
- 自然语言处理自然语言处理.
- 知识表示 知识表示
背景情况:
- 生成性预训练语言模型经常表现出事实幻觉和过时的知识.
- 开放领域的问答和文本生成需要提高准确性和知识的一致性.
研究的目的:
- 提出基于知识图的检索增强生成模型 (KG-RAG).
- 通过整合结构化知识图来提高生成模型的准确性和知识的及时性.
主要方法:
- 开发了一种双通道检索机制,用于非结构化文本的密集通道检索 (DPR) 和用于知识图检索的图形神经网络 (GNN).
- 利用路径注意机制来过相关的实体关系链来进行知识注入.
- 将结构化知识图集成到传统的检索增强生成 (RAG) 架构中.
主要成果:
- 在自然问题数据集中,KG-RAG显著提高了ROUGE-L (41.2至46.9) 和BLEU (31.5至38.7) 的得分.
- 事实指数增长了13.6%,表明知识的一致性得到了增强.
- 在PubMedQA上的医疗问题答案中获得了81.3%的准确性,比RAG提高了6.8%的点.
- 案例研究证实了KG-RAG通过整合知识图路径来产生逻辑和事实答案的能力.
结论:
- 在生成模型中,KG-RAG有效地减轻了事实幻觉,并提高了知识的及时性.
- 该模型在一般和专业领域的问答中表现出强的表现.
- 在智能问答系统,对话式人工智能和教育工具中,KG-RAG具有显著的应用潜力.
相关概念视频
Retrieval
392
Retrieval is the process of getting information out of memory storage and back into conscious awareness. This ability is essential for daily tasks like brushing hair and teeth, driving to work, and performing job duties. Retrieval occurs in three ways: recall, recognition, and relearning.
Recall involves accessing information without cues, such as during an essay test, where individuals must retrieve facts and concepts from memory unaided. Another example is remembering the name of a colleague...
Recall involves accessing information without cues, such as during an essay test, where individuals must retrieve facts and concepts from memory unaided. Another example is remembering the name of a colleague...
392
Storage
345
A schema is a mental framework that helps individuals organize and interpret information. Schemata, formed from previous experiences, influence how we process new information: how we encode it, the inferences we make, and how we retrieve it. For instance, a schema for what a typical classroom looks like might include desks, a teacher's desk, a whiteboard, and students in such an environment. This expectation helps us quickly understand and navigate new classrooms without needing to analyze...
345
Natural and Artificial Concepts
529
In psychology, concepts can be divided into two categories: natural and artificial. Natural concepts are formed through direct or indirect experiences. For example, consider the concept of snow. If you live in a place with regular snowfall, such as Essex Junction, Vermont, you know snow through direct experiences. You’ve seen it fall, touched it, shoveled it, and played in it. You recognize its texture, appearance, and even its smell. In contrast, if you live on an island like Saint...
529
Vector Algebra: Graphical Method
16.7K
Vectors can be multiplied by scalars, added to other vectors, or subtracted from other vectors. The vector sum of two (or more) vectors is called the resultant vector or, for short, the resultant.
We use the laws of geometry to construct resultant vectors, followed by trigonometry to find vector magnitudes and directions. For a geometric construction of the sum of two vectors in a plane, we follow the parallelogram rule. Suppose two vectors are at arbitrary positions. Translate either one of...
We use the laws of geometry to construct resultant vectors, followed by trigonometry to find vector magnitudes and directions. For a geometric construction of the sum of two vectors in a plane, we follow the parallelogram rule. Suppose two vectors are at arbitrary positions. Translate either one of...
16.7K
Concepts and Prototypes
483
The human nervous system handles vast amounts of information by translating sensory stimuli into neural impulses, which the brain processes, creating thoughts expressed through language or stored as memories. The brain also synthesizes information from emotions and memories, which significantly influence thoughts and behaviors. This intricate process creates a comprehensive mental picture.
The brain organizes this information using concepts, which are mental categories grouping linguistic data,...
The brain organizes this information using concepts, which are mental categories grouping linguistic data,...
483
Ogive Graph
6.6K
An ogive graph is sometimes called a cumulative frequency polygon. It is one type of frequency polygon that shows cumulative frequency. In other words, the cumulative percentages are added to the graph from left to right. An ogive graph plots cumulative frequency on the vertical y-axis and class boundaries along the horizontal x-axis. It’s very similar to a histogram; only instead of rectangles, an ogive displays a single point where the top right of the rectangle would be. Creating this...
6.6K


