mlsanityData to 7 Oct 2026

CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation

arXiv 2503.19878 ↗First posted 25 Mar 2025cs.CL cs.IRcited by 12

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

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.

Key facts. Cited by 12 papers in the map (data through 7 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.

Builds on

10 of 28 references.

References · 10

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  3. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 348
  4. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 258
  5. 2022OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and conceptscited by 166
  6. 2023Can Large Language Models Infer Causation from Correlation?cited by 142
  7. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 76
  8. 2024Causal Inference with Large Language Model: A Surveycited by 31
  9. 2024CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMscited by 20
  10. 2024Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughtscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 8.

12 papers.

  1. 2025Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learningcited by 50
  2. 2025HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Storescited by 3
  3. 2025GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generationcited by 3
  4. 2026HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAGcited by 3
  5. 2025Benchmarking Vector, Graph and Hybrid Retrieval Augmented Generation (RAG) Pipelines for Open Radio Access Networks (ORAN)cited by 2
  6. 2026Causal-Enhanced AI Agents for Medical Research Screeningcited by 0
  7. 2026Making medical vision-language models think causally across modalities with retrieval-augmented cross-modal reasoningcited by 0
  8. 2026Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generationcited by 0
  9. 2026XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generationcited by 0
  10. 2026Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inferencecited by 0
  11. 2026Structure Over Scale: Schema-Constrained Causal Graphs for RAGcited by 0
  12. 2026From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanismcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAG
  2. 2025CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation
  3. 2025Causal Graphs Meet Thoughts: Enhancing Complex Reasoning in Graph-Augmented LLMs
  4. 2024Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models
  5. 2024Probing Causality Manipulation of Large Language Models
  6. 2025Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG
  7. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
  8. 2025Retrieval Augmented Generation based Large Language Models for Causality Mining