Evaluating and Improving Graph to Text Generation with Large Language Models

• URL: http://arxiv.org/abs/2501.14497v2
• Date: Fri, 14 Feb 2025 12:38:15 GMT
• Title: Evaluating and Improving Graph to Text Generation with Large Language Models
• Authors: Jie He, Yijun Yang, Wanqiu Long, Deyi Xiong, Victor Gutierrez-Basulto, Jeff Z. Pan,
• Abstract summary: Large language models (LLMs) have demonstrated immense potential across various tasks. We conduct a comprehensive evaluation of prompting current open-source LLMs on graph-to-text generation tasks. We introduce a new graph-to-text dataset, PlanGTG, annotated with two sub-tasks: reordering and attribution.
• Score: 46.529034150391595
• License:
• Abstract: Large language models (LLMs) have demonstrated immense potential across various tasks. However, research for exploring and improving the capabilities of LLMs in interpreting graph structures remains limited. To address this gap, we conduct a comprehensive evaluation of prompting current open-source LLMs on graph-to-text generation tasks. Although we explored the optimal prompting strategies and proposed a novel and effective diversity-difficulty-based few-shot sample selection method, we found that the improvements from tuning-free approaches were incremental, as LLMs struggle with planning on complex graphs, particularly those with a larger number of triplets. To further improve LLMs in planning with graph sequences and grounding in truth, we introduce a new graph-to-text dataset, PlanGTG, annotated with two sub-tasks: reordering and attribution. Through extensive automatic and human evaluations, we demonstrate significant improvements in the quality of generated text from both few-shot learning and fine-tuning perspectives using the PlanGTG dataset. Our study paves the way for new research directions in graph-to-text generation. PlanGTG datasets can be found in https://github.com/probe2/kg_text.

Related papers

• GT2Vec: Large Language Models as Multi-Modal Encoders for Text and Graph-Structured Data [42.18348019901044]
  GT2Vec is a framework that leverages Large Language Models to jointly encode text and graph data. Unlike prior work, we also introduce contrastive learning to align the graph and text spaces more effectively.
  arXiv  Detail & Related papers  (2024-10-15T03:40:20Z)
• Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning [28.660326096652437]
  We introduce AskGNN, a novel approach that bridges the gap between sequential text processing and graph-structured data. AskGNN employs a Graph Neural Network (GNN)-powered structure-enhanced retriever to select labeled nodes across graphs. Experiments across three tasks and seven LLMs demonstrate AskGNN's superior effectiveness in graph task performance.
  arXiv  Detail & Related papers  (2024-10-09T17:19:12Z)
• GRAG: Graph Retrieval-Augmented Generation [14.98084919101233]
  Graph Retrieval-Augmented Generation (GRAG) tackles the fundamental challenges in retrieving textual subgraphs. We propose a novel divide-and-conquer strategy that retrieves the optimal subgraph structure in linear time. Our approach significantly outperforms current state-of-the-art RAG methods.
  arXiv  Detail & Related papers  (2024-05-26T10:11:40Z)
• Parameter-Efficient Tuning Large Language Models for Graph Representation Learning [62.26278815157628]
  We introduce Graph-aware. Efficient Fine-Tuning - GPEFT, a novel approach for efficient graph representation learning. We use a graph neural network (GNN) to encode structural information from neighboring nodes into a graph prompt. We validate our approach through comprehensive experiments conducted on 8 different text-rich graphs, observing an average improvement of 2% in hit@1 and Mean Reciprocal Rank (MRR) in link prediction evaluations.
  arXiv  Detail & Related papers  (2024-04-28T18:36:59Z)
• Exploring the Potential of Large Language Models in Graph Generation [51.046188600990014]
  Graph generation requires large language models (LLMs) to generate graphs with given properties. This paper explores the abilities of LLMs for graph generation with systematical task designs and experiments. Our evaluations demonstrate that LLMs, particularly GPT-4, exhibit preliminary abilities in graph generation tasks.
  arXiv  Detail & Related papers  (2024-03-21T12:37:54Z)
• Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs [57.052160123387104]
  We present the Disentangled Graph-Text Learner (DGTL) model, which is able to enhance the reasoning and predicting capabilities of LLMs for TAGs. Our proposed DGTL model incorporates graph structure information through tailored disentangled graph neural network (GNN) layers. Experimental evaluations demonstrate the effectiveness of the proposed DGTL model on achieving superior or comparable performance over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-10-27T14:00:04Z)
• Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs [5.587264586806575]
  We propose a plug-and-play approach to empower text-attributed graphs through node generation using Large Language Models (LLMs) LLMs extract semantic information from labels and generate samples that belong to categories as exemplars. We employ an edge predictor to capture structural information inherent in the raw dataset and integrate the newly generated samples into the original graph.
  arXiv  Detail & Related papers  (2023-10-15T16:04:28Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Investigating Pretrained Language Models for Graph-to-Text Generation [55.55151069694146]
  Graph-to-text generation aims to generate fluent texts from graph-based data. We present a study across three graph domains: meaning representations, Wikipedia knowledge graphs (KGs) and scientific KGs. We show that the PLMs BART and T5 achieve new state-of-the-art results and that task-adaptive pretraining strategies improve their performance even further.
  arXiv  Detail & Related papers  (2020-07-16T16:05:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.