Metraipolis › archive › dc_8e35eee18353
KGCaRe: Explainable Complex Conditional Question Answering using Automatic Knowledge Graph Construction and Context Retrieval with LLMs — arXiv:2608.09779
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09779
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:50:30.186Z
- SHA-256 of the archived text
962a9b24a30a41599da5992b7620a88eefae5fdf5f7c6aee514defc116e7a96f- Stable URL of this page
https://metraipolis.com/documento/dc_8e35eee18353
How to cite
KGCaRe: Explainable Complex Conditional Question Answering using Automatic Knowledge Graph Construction and Context Retrieval with LLMs — arXiv:2608.09779 — arXiv (en), https://arxiv.org/abs/2608.09779 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8e35eee18353 (Metraipolis archive dc_8e35eee18353, sha256 962a9b24a30a41599da5992b7620a88eefae5fdf5f7c6aee514defc116e7a96f)
BibTeX
@misc{dc8e35eee18353,
title = {KGCaRe: Explainable Complex Conditional Question Answering using Automatic Knowledge Graph Construction and Context Retrieval with LLMs — arXiv:2608.09779},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09779},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8e35eee18353; sha256 962a9b24a30a41599da5992b7620a88eefae5fdf5f7c6aee514defc116e7a96f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09779. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Answering complex conditional questions using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) remains a challenge, particularly in domain-specific contexts where general-purpose LLMs and RAG tend to underperform. We hypothesize that augmenting RAG with unstructured and structured knowledge, extracted from both documents and knowledge graphs (KGs), can improve reasoning and answer accuracy for such tasks. To test this, we propose KGCaRe, a hybrid approach that combines neural retrieval with symbolic reasoning over LLM-generated KGs. KGCaRe constructs a KG from documents using a multi-prompt extraction strategy and stores it in a graph database. Simultaneously, the documents are embedded into a vector store to enable neural retrieval. KGCaRe performs innovative iterative graph traversal guided by the LLM to extract relevant triples, prune irrelevant information, and uses additional clue entities to traverse the graph again if the initial traversal does not provide satisfactory context to generate the answer. The relevant triples extracted from the KG in path form, along with semantically retrieved text passages, are then fed into custom KGCaRe prompts to generate answers to the complex conditional questions with explanations. We evaluate KGCaRe on two complex conditional QA datasets. Our results on these datasets show that KGCaRe consistently outperforms existing baselines, including Vanilla LLM, Code Prompt, Text Prompt, Think-on-Graph, Vanilla RAG, and HybridContextQA, across multiple LLMs such as Mistral, Mixtral, GPT-3.5, and GPT-4o. We publicly release the software pipeline that we developed to implement the proposed KGCaRe approach. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.09779 — 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 2026-10-19T08:49:41.943Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).