Knowledge-Aware Self-Correction in Language Models via Structured Memory Graphs

2025/07/07 by Saha, Swayamjit
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2507.04625

Abstract

Large Language Models (LLMs) are powerful yet prone to generating factual errors, commonly referred to as hallucinations. We present a lightweight, interpretable framework for knowledge-aware self-correction of LLM outputs using structured memory graphs based on RDF triples. Without retraining or fine-tuning, our method post-processes model outputs and corrects factual inconsistencies via external semantic memory. We demonstrate the approach using DistilGPT-2 and show promising results on simple factual prompts.

Citations

• Language Models are Few-Shot Learners
• Language Models as Knowledge Bases?
• COMET: Commonsense Transformers for Automatic Knowledge Graph\n Construction

Related

• Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting
• Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval
• Addressing Hallucinations in Language Models with Knowledge Graph Embeddings as an Additional Modality
• Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
• Aligning Knowledge Graphs and Language Models for Factual Accuracy