Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929554777440256 |
|---|---|
| author | Wang, Junjie Chen, Mingyang Hu, Binbin Yang, Dan Liu, Ziqi Shen, Yue Wei, Peng Zhang, Zhiqiang Gu, Jinjie Zhou, Jun Pan, Jeff Z. Zhang, Wen Chen, Huajun |
| author_facet | Wang, Junjie Chen, Mingyang Hu, Binbin Yang, Dan Liu, Ziqi Shen, Yue Wei, Peng Zhang, Zhiqiang Gu, Jinjie Zhou, Jun Pan, Jeff Z. Zhang, Wen Chen, Huajun |
| contents | Improving the performance of large language models (LLMs) in complex question-answering (QA) scenarios has always been a research focal point. Recent studies have attempted to enhance LLMs' performance by combining step-wise planning with external retrieval. While effective for advanced models like GPT-3.5, smaller LLMs face challenges in decomposing complex questions, necessitating supervised fine-tuning. Previous work has relied on manual annotation and knowledge distillation from teacher LLMs, which are time-consuming and not accurate enough. In this paper, we introduce a novel framework for enhancing LLMs' planning capabilities by using planning data derived from knowledge graphs (KGs). LLMs fine-tuned with this data have improved planning capabilities, better equipping them to handle complex QA tasks that involve retrieval. Evaluations on multiple datasets, including our newly proposed benchmark, highlight the effectiveness of our framework and the benefits of KG-derived planning data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14282 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs Wang, Junjie Chen, Mingyang Hu, Binbin Yang, Dan Liu, Ziqi Shen, Yue Wei, Peng Zhang, Zhiqiang Gu, Jinjie Zhou, Jun Pan, Jeff Z. Zhang, Wen Chen, Huajun Computation and Language Artificial Intelligence Improving the performance of large language models (LLMs) in complex question-answering (QA) scenarios has always been a research focal point. Recent studies have attempted to enhance LLMs' performance by combining step-wise planning with external retrieval. While effective for advanced models like GPT-3.5, smaller LLMs face challenges in decomposing complex questions, necessitating supervised fine-tuning. Previous work has relied on manual annotation and knowledge distillation from teacher LLMs, which are time-consuming and not accurate enough. In this paper, we introduce a novel framework for enhancing LLMs' planning capabilities by using planning data derived from knowledge graphs (KGs). LLMs fine-tuned with this data have improved planning capabilities, better equipping them to handle complex QA tasks that involve retrieval. Evaluations on multiple datasets, including our newly proposed benchmark, highlight the effectiveness of our framework and the benefits of KG-derived planning data. |
| title | Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.14282 |