mlsanityData to 7 Oct 2026

When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation

arXiv 2601.09241 ↗First posted 14 Jan 2026cs.CLcited by 1

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

Abstract (arXiv)

Knowledge Graph Retrieval-Augmented Generation (KG-RAG) extends the RAG paradigm by incorporating structured knowledge from knowledge graphs, enabling Large Language Models (LLMs) to perform more precise and explainable reasoning. While KG-RAG improves factual accuracy in complex tasks, existing KG-RAG models are often severely overconfident, producing high-confidence predictions even when retrieved sub-graphs are incomplete or unreliable, which raises concerns for deployment in high-stakes domains. To address this issue, we propose Ca2KG, a Causality-aware Calibration framework for KG-RAG. Ca2KG integrates counterfactual prompting, which exposes retrieval-dependent uncertainties in knowledge quality and reasoning reliability, with a panel-based re-scoring mechanism that stabilises predictions across interventions. Extensive experiments on two complex QA datasets demonstrate that Ca2KG consistently improves calibration while maintaining or even enhancing predictive accuracy.

Key facts. Cited by 1 paper 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 31 of its 49 references that are in the map. First posted on arXiv 14 Jan 2026.

Builds on

31 of 49 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation10 Sep
  2. 2024GRAG: Graph Retrieval-Augmented Generation26 May

Other references · 29

  1. 2017On Calibration of Modern Neural Networkscited by 4,860
  2. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  3. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  4. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  5. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  6. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  7. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  8. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  9. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 209
  10. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  11. 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
  12. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 115
17 more
  1. 2024What Large Language Models Know and What People Think They Knowcited by 109
  2. 2022Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysiscited by 104
  3. 2023Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Modelscited by 91
  4. 2024Evaluating Retrieval Quality in Retrieval-Augmented Generationcited by 90
  5. 2024Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoningcited by 44
  6. 2023KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Modelscited by 32
  7. 2022On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliencycited by 31
  8. 2024Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustmentcited by 29
  9. 2024Knowledge Graph-Enhanced Large Language Models via Path Selectioncited by 28
  10. 2023Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencodercited by 17
  11. 2022Causal Intervention Improves Implicit Sentiment Analysiscited by 16
  12. 2022Graph Learning for Anomaly Analytics: Algorithms, Applications, and Challengescited by 15
  13. 2024Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Frameworkcited by 12
  14. 2023Disentangled Representation for Causal Mediation Analysiscited by 10
  15. 2023Conditional Instrumental Variable Regression with Representation Learning for Causal Inferencecited by 8
  16. 2024Disentangled Representation Learning for Causal Inference with Instrumentscited by 6
  17. 2025Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustmentcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inferencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAG
  2. 2025What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge
  3. 2026EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation
  4. 2026XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation
  5. 2025Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs
  6. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  7. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
  8. 2025A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmented Generation