Guided Navigation in Knowledge-Dense Environments: Structured Semantic Exploration with Guidance Graphs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918124835569664 |
|---|---|
| author | Tao, Dehao Liu, Guangjie Weizheng Huang, Yongfeng jiang, Minghu |
| author_facet | Tao, Dehao Liu, Guangjie Weizheng Huang, Yongfeng jiang, Minghu |
| contents | While Large Language Models (LLMs) exhibit strong linguistic capabilities, their reliance on static knowledge and opaque reasoning processes limits their performance in knowledge intensive tasks. Knowledge graphs (KGs) offer a promising solution, but current exploration methods face a fundamental trade off: question guided approaches incur redundant exploration due to granularity mismatches, while clue guided methods fail to effectively leverage contextual information for complex scenarios. To address these limitations, we propose Guidance Graph guided Knowledge Exploration (GG Explore), a novel framework that introduces an intermediate Guidance Graph to bridge unstructured queries and structured knowledge retrieval. The Guidance Graph defines the retrieval space by abstracting the target knowledge' s structure while preserving broader semantic context, enabling precise and efficient exploration. Building upon the Guidance Graph, we develop: (1) Structural Alignment that filters incompatible candidates without LLM overhead, and (2) Context Aware Pruning that enforces semantic consistency with graph constraints. Extensive experiments show our method achieves superior efficiency and outperforms SOTA, especially on complex tasks, while maintaining strong performance with smaller LLMs, demonstrating practical value. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_10012 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Guided Navigation in Knowledge-Dense Environments: Structured Semantic Exploration with Guidance Graphs Tao, Dehao Liu, Guangjie Weizheng Huang, Yongfeng jiang, Minghu Computation and Language While Large Language Models (LLMs) exhibit strong linguistic capabilities, their reliance on static knowledge and opaque reasoning processes limits their performance in knowledge intensive tasks. Knowledge graphs (KGs) offer a promising solution, but current exploration methods face a fundamental trade off: question guided approaches incur redundant exploration due to granularity mismatches, while clue guided methods fail to effectively leverage contextual information for complex scenarios. To address these limitations, we propose Guidance Graph guided Knowledge Exploration (GG Explore), a novel framework that introduces an intermediate Guidance Graph to bridge unstructured queries and structured knowledge retrieval. The Guidance Graph defines the retrieval space by abstracting the target knowledge' s structure while preserving broader semantic context, enabling precise and efficient exploration. Building upon the Guidance Graph, we develop: (1) Structural Alignment that filters incompatible candidates without LLM overhead, and (2) Context Aware Pruning that enforces semantic consistency with graph constraints. Extensive experiments show our method achieves superior efficiency and outperforms SOTA, especially on complex tasks, while maintaining strong performance with smaller LLMs, demonstrating practical value. |
| title | Guided Navigation in Knowledge-Dense Environments: Structured Semantic Exploration with Guidance Graphs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.10012 |