LATIDIA · Investigación

OA-RAG: RAG agencial basado en ontología para el razonamiento LLM fiel

arXiv: 2610.36335v1Tipo de anuncio: nuevo Resumen: Los modelos de lenguaje grandes (LLM) funcionan bien en muchas tareas del mundo real, pero siguen siendo propensos a las alucinaciones, lo que limita su confiabilidad en dominios como la biomedicina y Heal

La noticia

arXiv:2610.36335v1 Announce Type: new Abstract: Large language models (LLMs) perform well across many real-world tasks but remain prone to hallucination, limiting their reliability in domains such as biomedicine and healthcare, where answers must be grounded in established knowledge. Retrieval-augmented generation (RAG) mitigates this problem by incorporating external information, but often overlooks logical relationships and relies heavily on the LLM's own reasoning, which can compromise answer faithfulness. We propose OA-RAG, an agent that integrates formal reasoning with LLM reasoning, drawing on both the logical structure and informal annotations of domain ontologies. For each answer, OA-RAG reports the ontology observations used as evidence and a model-assessed grounding level (entailed, supported, related, or