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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Joshi, Ratnesh Kumar, Sengupta, Sagnik, Ekbal, Asif
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929646779498496
author Joshi, Ratnesh Kumar
Sengupta, Sagnik
Ekbal, Asif
author_facet Joshi, Ratnesh Kumar
Sengupta, Sagnik
Ekbal, Asif
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18672
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle From Hallucinations to Facts: Enhancing Language Models with Curated Knowledge Graphs
Joshi, Ratnesh Kumar
Sengupta, Sagnik
Ekbal, Asif
Computation and Language
Artificial Intelligence
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.
title From Hallucinations to Facts: Enhancing Language Models with Curated Knowledge Graphs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.18672