Efficient Knowledge Infusion via KG-LLM Alignment
- URL: http://arxiv.org/abs/2406.03746v1
- Date: Thu, 6 Jun 2024 04:55:55 GMT
- Title: Efficient Knowledge Infusion via KG-LLM Alignment
- Authors: Zhouyu Jiang, Ling Zhong, Mengshu Sun, Jun Xu, Rui Sun, Hui Cai, Shuhan Luo, Zhiqiang Zhang,
- Abstract summary: Knowledge graph-retrievalaugmented method has been proven to be an effective and efficient technique for knowledge infusion.
Existing approaches face two primary challenges: knowledge mismatch between public available knowledge graphs and the specific domain of the task at hand, and poor information compliance of LLMs with knowledge graphs.
We propose a three-stage KG-LLM alignment strategyto enhance the LLM's capability to utilize information from knowledge graphs.
- Score: 10.735490041033113
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: To tackle the problem of domain-specific knowledge scarcity within large language models (LLMs), knowledge graph-retrievalaugmented method has been proven to be an effective and efficient technique for knowledge infusion. However, existing approaches face two primary challenges: knowledge mismatch between public available knowledge graphs and the specific domain of the task at hand, and poor information compliance of LLMs with knowledge graphs. In this paper, we leverage a small set of labeled samples and a large-scale corpus to efficiently construct domain-specific knowledge graphs by an LLM, addressing the issue of knowledge mismatch. Additionally, we propose a three-stage KG-LLM alignment strategyto enhance the LLM's capability to utilize information from knowledge graphs. We conduct experiments with a limited-sample setting on two biomedical question-answering datasets, and the results demonstrate that our approach outperforms existing baselines.
Related papers
- Knowledge Graph Structure as Prompt: Improving Small Language Models Capabilities for Knowledge-based Causal Discovery [10.573861741540853]
KG Structure as Prompt is a novel approach for integrating structural information from a knowledge graph, such as common neighbor nodes and metapaths, into prompt-based learning.
Experimental results on three types of biomedical and open-domain datasets under few-shot settings demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2024-07-26T14:07:00Z) - Knowledge Graph-Enhanced Large Language Models via Path Selection [58.228392005755026]
Large Language Models (LLMs) have shown unprecedented performance in various real-world applications.
LLMs are known to generate factually inaccurate outputs, a.k.a. the hallucination problem.
We propose a principled framework KELP with three stages to handle the above problems.
arXiv Detail & Related papers (2024-06-19T21:45:20Z) - Empowering Small-Scale Knowledge Graphs: A Strategy of Leveraging General-Purpose Knowledge Graphs for Enriched Embeddings [3.7759315989669058]
We introduce a framework for enriching embeddings of small-scale domain-specific Knowledge Graphs with well-established general-purpose KGs.
Experimental evaluations demonstrate a notable enhancement, with up to a 44% increase observed in the Hits@10 metric.
This relatively unexplored research direction can catalyze more frequent incorporation of KGs in knowledge-intensive tasks.
arXiv Detail & Related papers (2024-05-17T12:46:23Z) - Collaborative Knowledge Infusion for Low-resource Stance Detection [83.88515573352795]
Target-related knowledge is often needed to assist stance detection models.
We propose a collaborative knowledge infusion approach for low-resource stance detection tasks.
arXiv Detail & Related papers (2024-03-28T08:32:14Z) - Infusing Knowledge into Large Language Models with Contextual Prompts [5.865016596356753]
We propose a simple yet generalisable approach for knowledge infusion by generating prompts from the context in the input text.
Our experiments show the effectiveness of our approach which we evaluate by probing the fine-tuned LLMs.
arXiv Detail & Related papers (2024-03-03T11:19:26Z) - InfuserKI: Enhancing Large Language Models with Knowledge Graphs via
Infuser-Guided Knowledge Integration [61.554209059971576]
Large Language Models (LLMs) have shown remarkable open-generation capabilities across diverse domains.
Injecting new knowledge poses the risk of forgetting previously acquired knowledge.
We propose a novel Infuser-Guided Knowledge Integration framework.
arXiv Detail & Related papers (2024-02-18T03:36:26Z) - Beyond Factuality: A Comprehensive Evaluation of Large Language Models
as Knowledge Generators [78.63553017938911]
Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks.
However, community concerns abound regarding the factuality and potential implications of using this uncensored knowledge.
We introduce CONNER, designed to evaluate generated knowledge from six important perspectives.
arXiv Detail & Related papers (2023-10-11T08:22:37Z) - Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph
Propagation [68.13453771001522]
We propose a multimodal intensive ZSL framework that matches regions of images with corresponding semantic embeddings.
We conduct extensive experiments and evaluate our model on large-scale real-world data.
arXiv Detail & Related papers (2023-06-14T13:07:48Z) - Ontology-enhanced Prompt-tuning for Few-shot Learning [41.51144427728086]
Few-shot Learning is aimed to make predictions based on a limited number of samples.
Structured data such as knowledge graphs and ontology libraries has been leveraged to benefit the few-shot setting in various tasks.
arXiv Detail & Related papers (2022-01-27T05:41:36Z) - Knowledge-Aware Meta-learning for Low-Resource Text Classification [87.89624590579903]
This paper studies a low-resource text classification problem and bridges the gap between meta-training and meta-testing tasks.
We propose KGML to introduce additional representation for each sentence learned from the extracted sentence-specific knowledge graph.
arXiv Detail & Related papers (2021-09-10T07:20:43Z)
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.