arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.07630cs.LG
收藏

G-Retriever:用于文本图理解与问答的检索增强生成

G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering

National University of Singapore(新加坡国立大学);University of Notre Dame(圣母大学);Loyola Marymount University(洛约拉马利蒙特大学);New York University(纽约大学);Meta AI

Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh V. Chawla, Thomas Laurent, Yann LeCun, Xavier Bresson, Bryan Hooi

AI总结:

提出G-Retriever,首个针对文本图的检索增强生成框架,通过奖品收集斯坦纳树优化实现图问答,优于基线并缓解幻觉。

摘要:

给定一个带有文本属性的图,我们使用户能够“与他们的图聊天”:即通过对话界面询问关于图的问题。针对用户的问题,我们的方法提供文本回复并突出显示图的相关部分。虽然现有工作以各种方式整合了大型语言模型(LLM)和图神经网络(GNN),但它们大多集中于传统图任务(如节点、边和图分类),或在小规模或合成图上回答简单的图查询。相比之下,我们开发了一个灵活的问答框架,针对真实世界的文本图,适用于多种应用,包括场景图理解、常识推理和知识图谱推理。为实现这一目标,我们首先构建了一个图问答(GraphQA)基准,数据来自不同任务。然后,我们提出了G-Retriever方法,引入了首个针对通用文本图的检索增强生成(RAG)方法,可通过软提示进行微调以增强图理解。为了抵抗幻觉并允许文本图远超LLM上下文窗口大小,G-Retriever通过将此任务表述为奖品收集斯坦纳树优化问题,在图上进行RAG。实证评估表明,我们的方法在多个领域的文本图任务上优于基线,能很好地扩展到更大的图规模,并减轻了幻觉。我们的代码和数据集可在https://github.com/XiaoxinHe/G-Retriever获取。

英文摘要:

Given a graph with textual attributes, we enable users to `chat with their graph': that is, to ask questions about the graph using a conversational interface. In response to a user's questions, our method provides textual replies and highlights the relevant parts of the graph. While existing works integrate large language models (LLMs) and graph neural networks (GNNs) in various ways, they mostly focus on either conventional graph tasks (such as node, edge, and graph classification), or on answering simple graph queries on small or synthetic graphs. In contrast, we develop a flexible question-answering framework targeting real-world textual graphs, applicable to multiple applications including scene graph understanding, common sense reasoning, and knowledge graph reasoning. Toward this goal, we first develop a Graph Question Answering (GraphQA) benchmark with data collected from different tasks. Then, we propose our G-Retriever method, introducing the first retrieval-augmented generation (RAG) approach for general textual graphs, which can be fine-tuned to enhance graph understanding via soft prompting. To resist hallucination and to allow for textual graphs that greatly exceed the LLM's context window size, G-Retriever performs RAG over a graph by formulating this task as a Prize-Collecting Steiner Tree optimization problem. Empirical evaluations show that our method outperforms baselines on textual graph tasks from multiple domains, scales well with larger graph sizes, and mitigates hallucination.~\footnote{Our codes and datasets are available at: \url{https://github.com/XiaoxinHe/G-Retriever}}

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑