From Hallucinations to Facts: Enhancing Language Models with Curated Knowledge Graphs

TL;DR

This paper enhances language models by integrating curated knowledge graphs to reduce hallucinations, improve factual accuracy, and ensure responses are grounded in empirical data, thereby increasing trustworthiness.

Contribution

It introduces a method for constructing and integrating curated knowledge graphs from Wikipedia to improve language model factual grounding.

Findings

Significant reduction in hallucination rates.

Improved factual accuracy in generated responses.

Enhanced model trustworthiness and reliability.

Abstract

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.