CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916693620555776 |
|---|---|
| author | Khatibi, Elahe Wang, Ziyu Rahmani, Amir M. |
| author_facet | Khatibi, Elahe Wang, Ziyu Rahmani, Amir M. |
| contents | Retrieval-Augmented Generation (RAG) has significantly enhanced large language models (LLMs) in knowledge-intensive tasks by incorporating external knowledge retrieval. However, existing RAG frameworks primarily rely on semantic similarity and correlation-driven retrieval, limiting their ability to distinguish true causal relationships from spurious associations. This results in responses that may be factually grounded but fail to establish cause-and-effect mechanisms, leading to incomplete or misleading insights. To address this issue, we introduce Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation (CDF-RAG), a framework designed to improve causal consistency, factual accuracy, and explainability in generative reasoning. CDF-RAG iteratively refines queries, retrieves structured causal graphs, and enables multi-hop causal reasoning across interconnected knowledge sources. Additionally, it validates responses against causal pathways, ensuring logically coherent and factually grounded outputs. We evaluate CDF-RAG on four diverse datasets, demonstrating its ability to improve response accuracy and causal correctness over existing RAG-based methods. Our code is publicly available at https://github.com/ elakhatibi/CDF-RAG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_12560 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation Khatibi, Elahe Wang, Ziyu Rahmani, Amir M. Computation and Language Retrieval-Augmented Generation (RAG) has significantly enhanced large language models (LLMs) in knowledge-intensive tasks by incorporating external knowledge retrieval. However, existing RAG frameworks primarily rely on semantic similarity and correlation-driven retrieval, limiting their ability to distinguish true causal relationships from spurious associations. This results in responses that may be factually grounded but fail to establish cause-and-effect mechanisms, leading to incomplete or misleading insights. To address this issue, we introduce Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation (CDF-RAG), a framework designed to improve causal consistency, factual accuracy, and explainability in generative reasoning. CDF-RAG iteratively refines queries, retrieves structured causal graphs, and enables multi-hop causal reasoning across interconnected knowledge sources. Additionally, it validates responses against causal pathways, ensuring logically coherent and factually grounded outputs. We evaluate CDF-RAG on four diverse datasets, demonstrating its ability to improve response accuracy and causal correctness over existing RAG-based methods. Our code is publicly available at https://github.com/ elakhatibi/CDF-RAG. |
| title | CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.12560 |