CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914106971258880 |
|---|---|
| author | Wang, Nengbo Han, Xiaotian Singh, Jagdip Ma, Jing Chaudhary, Vipin |
| author_facet | Wang, Nengbo Han, Xiaotian Singh, Jagdip Ma, Jing Chaudhary, Vipin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19878 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation Wang, Nengbo Han, Xiaotian Singh, Jagdip Ma, Jing Chaudhary, Vipin Computation and Language Information Retrieval 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. |
| title | CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2503.19878 |