Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective

Ernests Lavrinovics, Russa Biswas, Johannes Bjerva, Katja Hose

TL;DR

The current use of KGs in LLM systems and future directions within each of these challenges are considered, as well as methods for knowledge integration and evaluating hallucinations.

Abstract

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 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.

Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective

TL;DR

The current use of KGs in LLM systems and future directions within each of these challenges are considered, as well as methods for knowledge integration and evaluating hallucinations.

Abstract

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 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.

Paper Structure

This paper contains 7 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Available Resources for Evaluating Hallucinations
  3. Feasibility of Hallucination Mitigation
  4. Detection of Hallucinations
  5. Methods for Integrating Knowledge from KGs in LLMs
  6. On Hallucination Evaluation
  7. Conclusions and Future Work

Figures (2)

  • Figure 1: Example of different types of hallucinations occurring in the same output zhang2023siren.
  • Figure 2: Our categorization of different stages at which external knowledge can be integrated in an LLM to mitigate hallucinations. *Decoding does not explicitly use KGs although it can be used to prioritize in-context knowledge (such as KG metadata).