Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.03626 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916931786768384 |
|---|---|
| author | Moghaddam, Zahra Zehtabi Sabeti Dehghani, Zeinab Rani, Maneeha Aslansefat, Koorosh Mishra, Bhupesh Kumar Kureshi, Rameez Raja Thakker, Dhavalkumar |
| author_facet | Moghaddam, Zahra Zehtabi Sabeti Dehghani, Zeinab Rani, Maneeha Aslansefat, Koorosh Mishra, Bhupesh Kumar Kureshi, Rameez Raja Thakker, Dhavalkumar |
| contents | Generative AI, such as Large Language Models (LLMs), has achieved impressive progress but still produces hallucinations and unverifiable claims, limiting reliability in sensitive domains. Retrieval-Augmented Generation (RAG) improves accuracy by grounding outputs in external knowledge, especially in domains like healthcare, where precision is vital. However, RAG remains opaque and essentially a black box, heavily dependent on data quality. We developed a method-agnostic, perturbation-based framework that provides token and component-level interoperability for Graph RAG using SMILE and named it as Knowledge-Graph (KG)-SMILE. By applying controlled perturbations, computing similarities, and training weighted linear surrogates, KG-SMILE identifies the graph entities and relations most influential to generated outputs, thereby making RAG more transparent. We evaluate KG-SMILE using comprehensive attribution metrics, including fidelity, faithfulness, consistency, stability, and accuracy. Our findings show that KG-SMILE produces stable, human-aligned explanations, demonstrating its capacity to balance model effectiveness with interpretability and thereby fostering greater transparency and trust in machine learning technologies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03626 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE Moghaddam, Zahra Zehtabi Sabeti Dehghani, Zeinab Rani, Maneeha Aslansefat, Koorosh Mishra, Bhupesh Kumar Kureshi, Rameez Raja Thakker, Dhavalkumar Artificial Intelligence Generative AI, such as Large Language Models (LLMs), has achieved impressive progress but still produces hallucinations and unverifiable claims, limiting reliability in sensitive domains. Retrieval-Augmented Generation (RAG) improves accuracy by grounding outputs in external knowledge, especially in domains like healthcare, where precision is vital. However, RAG remains opaque and essentially a black box, heavily dependent on data quality. We developed a method-agnostic, perturbation-based framework that provides token and component-level interoperability for Graph RAG using SMILE and named it as Knowledge-Graph (KG)-SMILE. By applying controlled perturbations, computing similarities, and training weighted linear surrogates, KG-SMILE identifies the graph entities and relations most influential to generated outputs, thereby making RAG more transparent. We evaluate KG-SMILE using comprehensive attribution metrics, including fidelity, faithfulness, consistency, stability, and accuracy. Our findings show that KG-SMILE produces stable, human-aligned explanations, demonstrating its capacity to balance model effectiveness with interpretability and thereby fostering greater transparency and trust in machine learning technologies. |
| title | Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.03626 |