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.
@article{arxiv.2406.14282,
title = {Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs},
author = {Junjie Wang and Mingyang Chen and Binbin Hu and Dan Yang and Ziqi Liu and Yue Shen and Peng Wei and Zhiqiang Zhang and Jinjie Gu and Jun Zhou and Jeff Z. Pan and Wen Zhang and Huajun Chen},
journal= {arXiv preprint arXiv:2406.14282},
year = {2024}
}