Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) based applications including automated text generation, question answering, chatbots, and others. However, they face a significant challenge: hallucinations, where models produce plausible-sounding but factually incorrect responses. This undermines trust and limits the applicability of LLMs in different domains. Knowledge Graphs (KGs), on the other hand, provide a structured collection of interconnected facts represented as entities (nodes) and their relationships (edges). In recent research, KGs have been leveraged to provide context that can fill gaps in an LLM’s understanding of certain topics offering a promising approach to mitigate hallucinations in LLMs, enhancing their reliability and accuracy while benefiting from their wide applicability. Nonetheless, it is still a very active area of research with various unresolved open problems. In this paper, we discuss these open challenges covering state-of-the-art datasets and benchmarks as well as methods for knowledge integration and evaluating hallucinations. In our discussion, we consider the current use of KGs in LLM systems and identify future directions within each of these challenges.

The entity type information in Knowledge Graphs (KGs) such as DBpedia, Freebase, etc. is often incomplete due to automated generation. Entity Typing is the task of assigning or inferring the semantic type of an entity in a KG. This paper introduces an approach named Cat2Type which exploits the Wikipedia Categories to predict the missing entity types in a KG. This work extracts information from Wikipedia Category names and the Wikipedia Category graph which are the sources of rich semantic information about the entities. In Cat2Type, the characteristic features of the entities encapsulated in Wikipedia Category names are exploited using Neural Language Models. On the other hand, a Wikipedia Category graph is constructed to capture the connection between the categories. The Node level representations are learned by optimizing the neighbourhood information on the Wikipedia category graph. These representations are then used for entity type prediction via classification. The performance of Cat2Type is assessed on two real-world benchmark datasets DBpedia630k and FIGER. The experiments depict that Cat2Type obtained a significant improvement over state-of-the-art approaches.

Knowledge Graphs (KGs) have recently gained attention for representing knowledge about a particular domain. Since its advent, the Linked Open Data (LOD) cloud has constantly been growing containing many KGs about many different domains such as government, scholarly data, biomedical domain, etc. Apart from facilitating the inter-connectivity of datasets in the LOD cloud, KGs have been used in a variety of machine learning and Natural Language Processing (NLP) based applications. However, the information present in the KGs are sparse and are often incomplete. Predicting the missing links between the entities is necessary to overcome this issue. Moreover, in the LOD cloud, information about the same entities is available in multiple KGs in different forms. But the information that these entities are the same across KGs is missing. The main focus of this thesis is to do Knowledge Graph Completion by tackling the link prediction tasks within a KG as well as across different KGs. To do so, the latent representation of KGs in a low dimensional vector space has been exploited to predict the missing information in order to complete the KGs.