Aligning Knowledge Graphs and Language Models for Factual Accuracy

TL;DR

This paper presents ALIGNed-LLM, a method that integrates knowledge graph embeddings into language models to enhance factual accuracy and reduce hallucinations, demonstrated through improved performance on benchmarks and a real-world financial case.

Contribution

Introducing ALIGNed-LLM, a novel approach that aligns knowledge graph embeddings with language models to improve factual grounding and reduce hallucinations.

Findings

Significant improvement on question-answering benchmarks.

Enhanced factual accuracy in a financial application.

Effective alignment of entity embeddings reduces hallucinations.

Abstract

Large language models like GPT-4, Gemini, and Claude have transformed natural language processing (NLP) tasks such as question answering, dialogue generation, summarization, and so forth; yet their susceptibility to hallucination stands as one of the major challenges. Among numerous approaches to overcome this challenge, integration of Knowledge Graphs (KGs) into language models has emerged as a promising solution as it provides structured, reliable, domain-specific, and up-to-date external information to the language models. In this paper, we introduce ALIGNed-LLM, a simple yet effective approach to improve language models' factuality via a lean strategy to infuse KGs into the latent space of language models inspired by LLaVA where visual and textual information is infused. We use embeddings from a pre-trained Knowledge Graph Embedding (KGE) model, such as TransE, and a trainable projection layer to align entity and text embeddings. This alignment enables the language model to distinguish between similar entities improving factual grounding and reducing hallucination. We tested our approach on three popular questions-answering benchmark datasets alongside language models of varying sizes, showing significant improvement. Furthermore, we applied our approach to a real-world financial use case from a large central bank in Europe, which demands high accuracy and precision, demonstrating a substantial improvement of the LLM answers.