Advances in Knowledge Graph Construction and Hallucination Detection

The field of knowledge graph construction and hallucination detection is rapidly advancing, with a focus on improving the quality and reliability of generated knowledge graphs. Recent developments have led to the creation of more efficient and effective pipelines for constructing knowledge graphs, such as those that utilize large language models and ontology-aware approaches. Additionally, there is a growing emphasis on detecting and mitigating hallucinations in generated text, particularly in high-stakes applications such as legal and regulatory domains. Noteworthy papers in this area include Wikontic, which proposes a multi-stage pipeline for constructing high-quality knowledge graphs, and HalluGraph, which introduces a graph-theoretic framework for auditable hallucination detection. Other notable papers include Graphing the Truth, which presents a framework for structured visualizations of knowledge graphs to detect hallucinations, and OntoMetric, which proposes an ontology-guided framework for automated ESG knowledge graph construction.

Sources

Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models

Graphing the Truth: Structured Visualizations for Automated Hallucination Detection in LLMs

Graph Queries from Natural Language using Constrained Language Models and Visual Editing

OntoMetric: An Ontology-Guided Framework for Automated ESG Knowledge Graph Construction

HalluGraph: Auditable Hallucination Detection for Legal RAG Systems via Knowledge Graph Alignment

Global AI Governance Overview: Understanding Regulatory Requirements Across Global Jurisdictions

Copyright in AI Pre-Training Data Filtering: Regulatory Landscape and Mitigation Strategies

Training Data Attribution for Image Generation using Ontology-Aligned Knowledge Graphs

Mapping Data Labour Supply Chain in Africa in an Era of Digital Apartheid: a Struggle for Recognition

Ask Safely: Privacy-Aware LLM Query Generation for Knowledge Graphs

Built with on top of