GraphRAG-Causal: A novel graph-augmented framework for causal reasoning and annotation in news

TL;DR

GraphRAG-Causal is a new framework that combines graph-based retrieval and large language models to improve causal reasoning in news analysis, especially in low-data scenarios.

Contribution

It introduces a novel pipeline that transforms news headlines into causal graphs, employs hybrid retrieval with Neo4j, and uses LLMs for causal classification, enhancing accuracy and robustness.

Findings

Achieves 82.1% F1-score on causal classification with few-shot learning.

Effectively combines semantic and structural cues for event retrieval.

Improves real-time news analysis and misinformation detection.

Abstract

GraphRAG-Causal introduces an innovative framework that combines graph-based retrieval with large language models to enhance causal reasoning in news analysis. Traditional NLP approaches often struggle with identifying complex, implicit causal links, especially in low-data scenarios. Our approach addresses these challenges by transforming annotated news headlines into structured causal knowledge graphs. It then employs a hybrid retrieval system that merges semantic embeddings with graph-based structural cues leveraging Neo4j to accurately match and retrieve relevant events. The framework is built on a three-stage pipeline: First, during Data Preparation, news sentences are meticulously annotated and converted into causal graphs capturing cause, effect, and trigger relationships. Next, the Graph Retrieval stage stores these graphs along with their embeddings in a Neo4j database and utilizes hybrid Cypher queries to efficiently identify events that share both semantic and structural similarities with a given query. Finally, the LLM Inference stage utilizes these retrieved causal graphs in a few-shot learning setup with XML-based prompting, enabling robust classification and tagging of causal relationships. Experimental evaluations demonstrate that GraphRAG-Causal achieves an impressive F1-score of 82.1% on causal classification using just 20 few-shot examples. This approach significantly boosts accuracy and consistency, making it highly suitable for real-time applications in news reliability assessment, misinformation detection, and policy analysis.