LLM Inference Enhanced by External Knowledge: A Survey
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_ | 1866916767787384832 |
|---|---|
| author | Lin, Yu-Hsuan Chen, Qian-Hui Cheng, Yi-Jie Zhang, Jia-Ren Liu, Yi-Hung Hsia, Liang-Yu Chen, Yun-Nung |
| author_facet | Lin, Yu-Hsuan Chen, Qian-Hui Cheng, Yi-Jie Zhang, Jia-Ren Liu, Yi-Hung Hsia, Liang-Yu Chen, Yun-Nung |
| contents | Recent advancements in large language models (LLMs) have enhanced natural-language reasoning. However, their limited parametric memory and susceptibility to hallucination present persistent challenges for tasks requiring accurate, context-based inference. To overcome these limitations, an increasing number of studies have proposed leveraging external knowledge to enhance LLMs. This study offers a systematic exploration of strategies for using external knowledge to enhance LLMs, beginning with a taxonomy that categorizes external knowledge into unstructured and structured data. We then focus on structured knowledge, presenting distinct taxonomies for tables and knowledge graphs (KGs), detailing their integration paradigms with LLMs, and reviewing representative methods. Our comparative analysis further highlights the trade-offs among interpretability, scalability, and performance, providing insights for developing trustworthy and generalizable knowledge-enhanced LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_24377 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM Inference Enhanced by External Knowledge: A Survey Lin, Yu-Hsuan Chen, Qian-Hui Cheng, Yi-Jie Zhang, Jia-Ren Liu, Yi-Hung Hsia, Liang-Yu Chen, Yun-Nung Computation and Language Recent advancements in large language models (LLMs) have enhanced natural-language reasoning. However, their limited parametric memory and susceptibility to hallucination present persistent challenges for tasks requiring accurate, context-based inference. To overcome these limitations, an increasing number of studies have proposed leveraging external knowledge to enhance LLMs. This study offers a systematic exploration of strategies for using external knowledge to enhance LLMs, beginning with a taxonomy that categorizes external knowledge into unstructured and structured data. We then focus on structured knowledge, presenting distinct taxonomies for tables and knowledge graphs (KGs), detailing their integration paradigms with LLMs, and reviewing representative methods. Our comparative analysis further highlights the trade-offs among interpretability, scalability, and performance, providing insights for developing trustworthy and generalizable knowledge-enhanced LLMs. |
| title | LLM Inference Enhanced by External Knowledge: A Survey |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.24377 |