A Human-in-the-Loop, LLM-Centered Architecture for Knowledge-Graph Question Answering
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910013931388928 |
|---|---|
| author | Pusch, Larissa Courtiol, Alexandre Conrad, Tim |
| author_facet | Pusch, Larissa Courtiol, Alexandre Conrad, Tim |
| contents | Large Language Models (LLMs) excel at language understanding but remain limited in knowledge-intensive domains due to hallucinations, outdated information, and limited explainability. Text-based retrieval-augmented generation (RAG) helps ground model outputs in external sources but struggles with multi-hop reasoning. Knowledge Graphs (KGs), in contrast, support precise, explainable querying, yet require a knowledge of query languages. This work introduces an interactive framework in which LLMs generate and explain Cypher graph queries and users iteratively refine them through natural language. Applied to real-world KGs, the framework improves accessibility to complex datasets while preserving factual accuracy and semantic rigor and provides insight into how model performance varies across domains. Our core quantitative evaluation is a 90-query benchmark on a synthetic movie KG that measures query explanation quality and fault detection across multiple LLMs, complemented by two smaller real-life query-generation experiments on a Hyena KG and the MaRDI (Mathematical Research Data Initiative) KG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05512 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Human-in-the-Loop, LLM-Centered Architecture for Knowledge-Graph Question Answering Pusch, Larissa Courtiol, Alexandre Conrad, Tim Computation and Language Information Retrieval Large Language Models (LLMs) excel at language understanding but remain limited in knowledge-intensive domains due to hallucinations, outdated information, and limited explainability. Text-based retrieval-augmented generation (RAG) helps ground model outputs in external sources but struggles with multi-hop reasoning. Knowledge Graphs (KGs), in contrast, support precise, explainable querying, yet require a knowledge of query languages. This work introduces an interactive framework in which LLMs generate and explain Cypher graph queries and users iteratively refine them through natural language. Applied to real-world KGs, the framework improves accessibility to complex datasets while preserving factual accuracy and semantic rigor and provides insight into how model performance varies across domains. Our core quantitative evaluation is a 90-query benchmark on a synthetic movie KG that measures query explanation quality and fault detection across multiple LLMs, complemented by two smaller real-life query-generation experiments on a Hyena KG and the MaRDI (Mathematical Research Data Initiative) KG. |
| title | A Human-in-the-Loop, LLM-Centered Architecture for Knowledge-Graph Question Answering |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2602.05512 |