How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback
- URL: http://arxiv.org/abs/2501.15378v1
- Date: Sun, 26 Jan 2025 03:27:11 GMT
- Title: How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback
- Authors: Manzong Huang, Chenyang Bu, Yi He, Xindong Wu,
- Abstract summary: This paper proposes the Triple Context Restoration and Query-driven Feedback framework.
It reconstructs the textual context underlying each triple to mitigate information loss.
It achieves a 29.1% improvement in Exact Match and a 15.5% improvement in F1 over its state-of-the-art GraphRAG competitors.
- Score: 12.250007669492753
- License:
- Abstract: Knowledge Graph (KG)-augmented Large Language Models (LLMs) have recently propelled significant advances in complex reasoning tasks, thanks to their broad domain knowledge and contextual awareness. Unfortunately, current methods often assume KGs to be complete, which is impractical given the inherent limitations of KG construction and the potential loss of contextual cues when converting unstructured text into entity-relation triples. In response, this paper proposes the Triple Context Restoration and Query-driven Feedback (TCR-QF) framework, which reconstructs the textual context underlying each triple to mitigate information loss, while dynamically refining the KG structure by iteratively incorporating query-relevant missing knowledge. Experiments on five benchmark question-answering datasets substantiate the effectiveness of TCR-QF in KG and LLM integration, where itachieves a 29.1% improvement in Exact Match and a 15.5% improvement in F1 over its state-of-the-art GraphRAG competitors.
Related papers
- GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion [52.026016846945424]
We propose a new method called GLTW, which encodes the structural information of KGs and merges it with Large Language Models.
Specifically, we introduce an improved Graph Transformer (iGT) that effectively encodes subgraphs with both local and global structural information.
Also, we develop a subgraph-based multi-classification training objective, using all entities within KG as classification objects, to boost learning efficiency.
arXiv Detail & Related papers (2025-02-17T06:02:59Z) - Efficient Relational Context Perception for Knowledge Graph Completion [25.903926643251076]
Knowledge Graphs (KGs) provide a structured representation of knowledge but often suffer from challenges of incompleteness.
Previous knowledge graph embedding models are limited in their ability to capture expressive features.
We propose Triple Receptance Perception architecture to model sequential information, enabling the learning of dynamic context.
arXiv Detail & Related papers (2024-12-31T11:25:58Z) - A Contextualized BERT model for Knowledge Graph Completion [0.0]
We introduce a contextualized BERT model for Knowledge Graph Completion (KGC)
Our model eliminates the need for entity descriptions and negative triplet sampling, reducing computational demands while improving performance.
Our model outperforms state-of-the-art methods on standard datasets, improving Hit@1 by 5.3% and 4.88% on FB15k-237 and WN18RR respectively.
arXiv Detail & Related papers (2024-12-15T02:03:16Z) - Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models [83.28737898989694]
Large language models (LLMs) struggle with faithful reasoning due to knowledge gaps and hallucinations.
We introduce graph-constrained reasoning (GCR), a novel framework that bridges structured knowledge in KGs with unstructured reasoning in LLMs.
GCR achieves state-of-the-art performance and exhibits strong zero-shot generalizability to unseen KGs without additional training.
arXiv Detail & Related papers (2024-10-16T22:55:17Z) - Context Graph [8.02985792541121]
We present a context graph reasoning textbfCGR$3$ paradigm that leverages large language models (LLMs) to retrieve candidate entities and related contexts.
Our experimental results demonstrate that CGR$3$ significantly improves performance on KG completion (KGC) and KG question answering (KGQA) tasks.
arXiv Detail & Related papers (2024-06-17T02:59:19Z) - Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering [87.67177556994525]
We propose a training-free method called Generate-on-Graph (GoG) to generate new factual triples while exploring Knowledge Graphs (KGs)
GoG performs reasoning through a Thinking-Searching-Generating framework, which treats LLM as both Agent and KG in IKGQA.
arXiv Detail & Related papers (2024-04-23T04:47:22Z) - Multi-perspective Improvement of Knowledge Graph Completion with Large
Language Models [95.31941227776711]
We propose MPIKGC to compensate for the deficiency of contextualized knowledge and improve KGC by querying large language models (LLMs)
We conducted extensive evaluation of our framework based on four description-based KGC models and four datasets, for both link prediction and triplet classification tasks.
arXiv Detail & Related papers (2024-03-04T12:16:15Z) - Federated Knowledge Graph Completion via Latent Embedding Sharing and
Tensor Factorization [51.286715478399515]
Federated Latent Embedding factorization (FLEST) is a novel approach using federated factorization for KG completion.
FLEST decomposes the embedding matrix and enables sharing of latent dictionary embeddings to lower privacy risks.
Empirical results demonstrate FLEST's effectiveness and efficiency, offering a balanced solution between performance and privacy.
arXiv Detail & Related papers (2023-11-17T06:03:56Z) - KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using
Large Language Models [18.20425100517317]
We propose KG-GPT, a framework leveraging large language models for tasks employing knowledge graphs.
KG-GPT comprises three steps: Sentence, Graph Retrieval, and Inference, each aimed at partitioning sentences, retrieving relevant graph components, and deriving logical conclusions.
We evaluate KG-GPT using KG-based fact verification and KGQA benchmarks, with the model showing competitive and robust performance, even outperforming several fully-supervised models.
arXiv Detail & Related papers (2023-10-17T12:51:35Z) - KG-ECO: Knowledge Graph Enhanced Entity Correction for Query Rewriting [15.243664083941287]
In this work, we propose KG-ECO: Knowledge Graph enhanced Entity COrrection for query rewriting.
To boost the model performance, we incorporate Knowledge Graph (KG) to provide entity structural information.
Experimental results show that our approach yields a clear performance gain over two baselines.
arXiv Detail & Related papers (2023-02-21T05:42:06Z) - Explainable Sparse Knowledge Graph Completion via High-order Graph
Reasoning Network [111.67744771462873]
This paper proposes a novel explainable model for sparse Knowledge Graphs (KGs)
It combines high-order reasoning into a graph convolutional network, namely HoGRN.
It can not only improve the generalization ability to mitigate the information insufficiency issue but also provide interpretability.
arXiv Detail & Related papers (2022-07-14T10:16:56Z)
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.