Metraipolis › archive › dc_14342b3bc313
Knowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question Answering — arXiv:2609.18317
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18317
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T13:49:26.124Z
- SHA-256 of the archived text
d47eb2baac1de772faebefec5822d7232c3d8e65e04c8ee17d8b37c7f4495901- Stable URL of this page
https://metraipolis.com/documento/dc_14342b3bc313
How to cite
Knowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question Answering — arXiv:2609.18317 — arXiv (en), https://arxiv.org/abs/2609.18317 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_14342b3bc313 (Metraipolis archive dc_14342b3bc313, sha256 d47eb2baac1de772faebefec5822d7232c3d8e65e04c8ee17d8b37c7f4495901)
BibTeX
@misc{dc14342b3bc313,
title = {Knowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question Answering — arXiv:2609.18317},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18317},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_14342b3bc313; sha256 d47eb2baac1de772faebefec5822d7232c3d8e65e04c8ee17d8b37c7f4495901},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18317. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.18317 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T13:48:24.314Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).