# CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2503.19878 · HTML: https://mlsanity.com/paper/2503.19878/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 10 of 10)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts](https://mlsanity.com/paper/2205.01833/) (2022)
- [Can Large Language Models Infer Causation from Correlation?](https://mlsanity.com/paper/2306.05836/) (2023)
- [Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting](https://mlsanity.com/paper/2407.08223/) (2024)
- [Causal Inference with Large Language Model: A Survey](https://mlsanity.com/paper/2409.09822/) (2024)
- [CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMs](https://mlsanity.com/paper/2404.06349/) (2024)
- [Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts](https://mlsanity.com/paper/2405.19893/) (2024)

## Built on by (most cited first, 12 of 12)

- [Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning](https://mlsanity.com/paper/2507.21892/) (2025)
- [HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Stores](https://mlsanity.com/paper/2509.21336/) (2025)
- [GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.22009/) (2025)
- [HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG](https://mlsanity.com/paper/2601.17755/) (2026)
- [Benchmarking Vector, Graph and Hybrid Retrieval Augmented Generation (RAG) Pipelines for Open Radio Access Networks (ORAN)](https://mlsanity.com/paper/2507.03608/) (2025)
- [Causal-Enhanced AI Agents for Medical Research Screening](https://mlsanity.com/paper/2601.02814/) (2026)
- [Making medical vision-language models think causally across modalities with retrieval-augmented cross-modal reasoning](https://mlsanity.com/paper/2601.18356/) (2026)
- [Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.03174/) (2026)
- [XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.24623/) (2026)
- [Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference](https://mlsanity.com/paper/2607.18225/) (2026)
- [Structure Over Scale: Schema-Constrained Causal Graphs for RAG](https://mlsanity.com/paper/2607.22592/) (2026)
- [From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism](https://mlsanity.com/paper/2608.21702/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have revolutionized natural language processing (NLP), particularly through Retrieval-Augmented Generation (RAG), which enhances LLM capabilities by integrating external knowledge. However, traditional RAG systems face critical limitations, including disrupted contextual integrity due to text chunking, and over-reliance on semantic similarity for retrieval. To address these issues, we propose CausalRAG, a novel framework that incorporates causal graphs into the retrieval process. By constructing and tracing causal relationships, CausalRAG preserves contextual continuity and improves retrieval precision, leading to more accurate and interpretable responses. We evaluate CausalRAG against regular RAG and graph-based RAG approaches, demonstrating its superiority across several metrics. Our findings suggest that grounding retrieval in causal reasoning provides a promising approach to knowledge-intensive tasks.