Graph Neural Network Enhanced Retrieval for Question Answering of LLMs
- URL: http://arxiv.org/abs/2406.06572v2
- Date: Fri, 18 Oct 2024 08:20:38 GMT
- Title: Graph Neural Network Enhanced Retrieval for Question Answering of LLMs
- Authors: Zijian Li, Qingyan Guo, Jiawei Shao, Lei Song, Jiang Bian, Jun Zhang, Rui Wang,
- Abstract summary: Existing retrieval methods divide reference documents into passages, treating them in isolation.
These passages, however, are often interrelated, such as passages that are contiguous or share the same keywords.
We propose a novel retrieval method, called GNN-Ret, which leverages graph neural networks (GNNs) to enhance retrieval by exploiting the relatedness between passages.
- Score: 19.24603296717601
- License:
- Abstract: Retrieval augmented generation has revolutionized large language model (LLM) outputs by providing factual supports. Nevertheless, it struggles to capture all the necessary knowledge for complex reasoning questions. Existing retrieval methods typically divide reference documents into passages, treating them in isolation. These passages, however, are often interrelated, such as passages that are contiguous or share the same keywords. Therefore, it is crucial to recognize such relatedness for enhancing the retrieval process. In this paper, we propose a novel retrieval method, called GNN-Ret, which leverages graph neural networks (GNNs) to enhance retrieval by exploiting the relatedness between passages. Specifically, we first construct a graph of passages by connecting passages that are structure-related or keyword-related. A graph neural network (GNN) is then leveraged to exploit the relationships between passages and improve the retrieval of supporting passages. Furthermore, we extend our method to handle multi-hop reasoning questions using a recurrent graph neural network (RGNN), named RGNN-Ret. At each step, RGNN-Ret integrates the graphs of passages from previous steps, thereby enhancing the retrieval of supporting passages. Extensive experiments on benchmark datasets demonstrate that GNN-Ret achieves higher accuracy for question answering with a single query of LLMs than strong baselines that require multiple queries, and RGNN-Ret further improves accuracy and achieves state-of-the-art performance, with up to 10.4% accuracy improvement on the 2WikiMQA dataset.
Related papers
- Graph Neural Re-Ranking via Corpus Graph [12.309841763251406]
Graph Neural Re-Ranking (GNRR) is a pipeline based on Graph Neural Networks (GNNs) that enables each query to consider documents distribution during inference.
We demonstrate that GNNs effectively capture cross-document interactions, improving performance on popular ranking metrics.
arXiv Detail & Related papers (2024-06-17T16:38:19Z) - A Comprehensive Study on Large-Scale Graph Training: Benchmarking and
Rethinking [124.21408098724551]
Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs)
We present a new ensembling training manner, named EnGCN, to address the existing issues.
Our proposed method has achieved new state-of-the-art (SOTA) performance on large-scale datasets.
arXiv Detail & Related papers (2022-10-14T03:43:05Z) - Relation Embedding based Graph Neural Networks for Handling
Heterogeneous Graph [58.99478502486377]
We propose a simple yet efficient framework to make the homogeneous GNNs have adequate ability to handle heterogeneous graphs.
Specifically, we propose Relation Embedding based Graph Neural Networks (RE-GNNs), which employ only one parameter per relation to embed the importance of edge type relations and self-loop connections.
arXiv Detail & Related papers (2022-09-23T05:24:18Z) - Long Range Graph Benchmark [32.317725340138104]
MP-GNNs that simply rely on 1-hop message passing often fare better in several existing graph benchmarks.
We benchmark both baseline GNNs and Graph Transformer networks to verify that the models which capture long-range dependencies perform significantly better on these tasks.
arXiv Detail & Related papers (2022-06-16T13:33:22Z) - Automatic Relation-aware Graph Network Proliferation [182.30735195376792]
We propose Automatic Relation-aware Graph Network Proliferation (ARGNP) for efficiently searching GNNs.
These operations can extract hierarchical node/relational information and provide anisotropic guidance for message passing on a graph.
Experiments on six datasets for four graph learning tasks demonstrate that GNNs produced by our method are superior to the current state-of-the-art hand-crafted and search-based GNNs.
arXiv Detail & Related papers (2022-05-31T10:38:04Z) - KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain
Question Answering [68.00631278030627]
We propose a novel method KG-FiD, which filters noisy passages by leveraging the structural relationship among the retrieved passages with a knowledge graph.
We show that KG-FiD can improve vanilla FiD by up to 1.5% on answer exact match score and achieve comparable performance with FiD with only 40% of computation cost.
arXiv Detail & Related papers (2021-10-08T18:39:59Z) - MrGCN: Mirror Graph Convolution Network for Relation Extraction with
Long-Term Dependencies [32.27755470353054]
In relation extraction, dependency trees that contain rich syntactic clues have been widely used to help capture long-term dependencies in text.
We propose the Mirror Graph Convolution Network (MrGCN), a GNN model with pooling-unpooling structures tailored to relation extraction.
Experiments on two datasets demonstrate the effectiveness of our method, showing significant improvements over previous results.
arXiv Detail & Related papers (2021-01-01T00:52:53Z) - Analyzing the Performance of Graph Neural Networks with Pipe Parallelism [2.269587850533721]
We focus on Graph Neural Networks (GNNs) that have found great success in tasks such as node or edge classification and link prediction.
New approaches for processing larger networks are needed to advance graph techniques.
We study how GNNs could be parallelized using existing tools and frameworks that are known to be successful in the deep learning community.
arXiv Detail & Related papers (2020-12-20T04:20:38Z) - Policy-GNN: Aggregation Optimization for Graph Neural Networks [60.50932472042379]
Graph neural networks (GNNs) aim to model the local graph structures and capture the hierarchical patterns by aggregating the information from neighbors.
It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features.
We propose Policy-GNN, a meta-policy framework that models the sampling procedure and message passing of GNNs into a combined learning process.
arXiv Detail & Related papers (2020-06-26T17:03:06Z) - Learning to Hash with Graph Neural Networks for Recommender Systems [103.82479899868191]
Graph representation learning has attracted much attention in supporting high quality candidate search at scale.
Despite its effectiveness in learning embedding vectors for objects in the user-item interaction network, the computational costs to infer users' preferences in continuous embedding space are tremendous.
We propose a simple yet effective discrete representation learning framework to jointly learn continuous and discrete codes.
arXiv Detail & Related papers (2020-03-04T06:59:56Z)
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.