aiqbench analysis
This research compares Knowledge Graph-based augmentation against standard Retrieval-Augmented Generation (RAG) for answering culturally specific questions, particularly in underrepresented regions like Latin America. The study demonstrates that structured graphs can significantly reduce LLM errors and offer better explainability while maintaining multilingual capabilities without fine-tuning.
Knowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question Answering
arXiv:2609.18317v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from a long-tail deficit: culturally specific facts, particularly those concerning underrepresented regions such as Latin America, appear too rarely in pretraining corpora to be reliably memorized. Retrieval-Augmented Generation (RAG) addresses this by grounding generation in external text, but structured alternatives such as Knowledge Graphs (KGs) offer tighter control over what enters the context, along with potential gains in explainability and updatability. We benchmark Graph-RAG against standard RAG on LatamQA, a culturally grounded multiple-choice dataset spanning eight thematic categories. The graphs are built end-to-end from Wikipedia articles with KGGen, a recent open-domain extractor, without manual curation in our main setting. G-Retriever is competitive with RAG and reduces the error of the base LLM by 72\% with a standard KG and 78\% with a benchmark-aware variant, the gap to RAG narrowing further as the graph is oriented toward task-relevant content. The trained projection transfers zero-shot to Portuguese without target-language fine-tuning, indicating multilingual reach.
Abstract:Large language models (LLMs) suffer from a long-tail deficit: culturally specific facts, particularly those concerning underrepresented regions such as Latin America, appear too rarely in pretraining corpora to be reliably memorized. Retrieval-Augmented Generation (RAG) addresses this by grounding generation in external text, but structured alternatives such as Knowledge Graphs (KGs) offer tighter control over what enters the context, along with potential gains in explainability and updatability. We benchmark Graph-RAG against standard RAG on LatamQA, a culturally grounded multiple-choice dataset spanning eight thematic categories. The graphs are built end-to-end from Wikipedia articles with KGGen, a recent open-domain extractor, without manual curation in our main setting. G-Retriever is competitive with RAG and reduces the error of the base LLM by 72\% with a standard KG and 78\% with a benchmark-aware variant, the gap to RAG narrowing further as the graph is oriented toward task-relevant content. The trained projection transfers zero-shot to Portuguese without target-language fine-tuning, indicating multilingual reach.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2609.18317 [cs.CL]
(or arXiv:2609.18317v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.18317 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 254 words
Related coverage
Build enterprise search for agents with Amazon Bedrock Managed Knowledge Base
AWS · Jul 16, 2026
Presentation: Platform Teams Enabling AI - MCP/Multi-Agentic Tools across Linkedin
InfoQ · Jun 5, 2026
From Vector Search to Agentic RAG: Building an Enterprise Research Analyst with hipVS
AMD · Jul 15, 2026
Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation
arXiv · Jun 4, 2026