Summary of Learning to Plan For Retrieval-augmented Large Language Models From Knowledge Graphs, by Junjie Wang et al.
Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs
by Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Jeff Z. Pan, Wen Zhang, Huajun Chen
First submitted to arxiv on: 20 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper focuses on improving large language models’ (LLMs) performance in complex question-answering (QA) scenarios. Recent studies have attempted to enhance LLMs by combining step-wise planning with external retrieval, but smaller LLMs face challenges in decomposing complex questions and require supervised fine-tuning. The authors introduce a novel framework that enhances LLMs’ planning capabilities using planning data derived from knowledge graphs (KGs). LLMs fine-tuned with this data exhibit improved planning capabilities, better equipping them to handle complex QA tasks involving retrieval. Evaluations on multiple datasets, including a newly proposed benchmark, demonstrate the effectiveness of the framework and the benefits of KG-derived planning data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research paper is about making computers better at answering complex questions. Right now, big computer models are good at answering simple questions but struggle with harder ones. The authors found a new way to help smaller computer models do better by using special data from the internet. This helps the computer models plan and think more like humans when answering complex questions. They tested this new method on many different question types and showed that it really works! |
Keywords
» Artificial intelligence » Fine tuning » Question answering » Supervised
