Geographic Named Entity Matching and Evaluation Recommendation Using Multi-Objective Tasks: A Study Integrating a Large Language Model (LLM) and Retrieval-Augmented Generation (RAG)

Geographical named entity matching, a crucial step in address encoding, aims to enhance address resolution accuracy through the precise identification and linkage of geographical named entity data. However, existing approaches tend to ignore the spatial information of entities, leading to misclassif...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiajun Zhang, Junjie Fang, Chengkun Zhang, Wei Zhang, Huanbing Ren, Liuchang Xu
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:https://www.mdpi.com/2220-9964/14/3/95
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849343019417862144
author Jiajun Zhang
Junjie Fang
Chengkun Zhang
Wei Zhang
Huanbing Ren
Liuchang Xu
author_facet Jiajun Zhang
Junjie Fang
Chengkun Zhang
Wei Zhang
Huanbing Ren
Liuchang Xu
author_sort Jiajun Zhang
collection DOAJ
description Geographical named entity matching, a crucial step in address encoding, aims to enhance address resolution accuracy through the precise identification and linkage of geographical named entity data. However, existing approaches tend to ignore the spatial information of entities, leading to misclassification. Drawing on the human process of searching for addresses, this study proposes a multi-objective learning model named GNEMM that integrates the semantic and spatial information of geographical named entities. To further mimic the human cognitive process during address search, it incorporates the Retrieval-Augmented Generation (RAG) technique. By integrating newly added external address data with an advanced large language model (LLM) like GPT-4, it achieves precise address evaluation and recommendation. The model was tested using a standard geographical named entity dataset from Shandong Province, focusing on three sub-tasks: element segmentation, matching, and spatial similarity score prediction. The experimental results indicate that the method achieves a geographical named entity matching accuracy of up to 99%, with improvements of 10% and 5% in the segmentation and prediction sub-tasks. GNEMM performs best in address-matching tasks of various scales, and the vectors extracted by GNEMM perform best in the downstream retrieval and matching of various address types, which verifies its applicability in geographical named entity recommendation applications.
format Article
id doaj-art-9193dcc13662448dbb6be61bf033a95c
institution Kabale University
issn 2220-9964
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj-art-9193dcc13662448dbb6be61bf033a95c2025-08-20T03:43:11ZengMDPI AGISPRS International Journal of Geo-Information2220-99642025-02-011439510.3390/ijgi14030095Geographic Named Entity Matching and Evaluation Recommendation Using Multi-Objective Tasks: A Study Integrating a Large Language Model (LLM) and Retrieval-Augmented Generation (RAG)Jiajun Zhang0Junjie Fang1Chengkun Zhang2Wei Zhang3Huanbing Ren4Liuchang Xu5School of Mathematics and Computer Science, Zhejiang Agriculture and Forestry University, Hangzhou 311300, ChinaCSSC (Zhejiang) Ocean Technology Co., Ltd., Hangzhou 316000, ChinaSchool of Earth Sciences, Zhejiang University, Hangzhou 310058, ChinaCollege of Oceanography and Space Informatics, China University of Petroleum, Qingdao 266580, ChinaSchool of Mathematics and Computer Science, Zhejiang Agriculture and Forestry University, Hangzhou 311300, ChinaSchool of Mathematics and Computer Science, Zhejiang Agriculture and Forestry University, Hangzhou 311300, ChinaGeographical named entity matching, a crucial step in address encoding, aims to enhance address resolution accuracy through the precise identification and linkage of geographical named entity data. However, existing approaches tend to ignore the spatial information of entities, leading to misclassification. Drawing on the human process of searching for addresses, this study proposes a multi-objective learning model named GNEMM that integrates the semantic and spatial information of geographical named entities. To further mimic the human cognitive process during address search, it incorporates the Retrieval-Augmented Generation (RAG) technique. By integrating newly added external address data with an advanced large language model (LLM) like GPT-4, it achieves precise address evaluation and recommendation. The model was tested using a standard geographical named entity dataset from Shandong Province, focusing on three sub-tasks: element segmentation, matching, and spatial similarity score prediction. The experimental results indicate that the method achieves a geographical named entity matching accuracy of up to 99%, with improvements of 10% and 5% in the segmentation and prediction sub-tasks. GNEMM performs best in address-matching tasks of various scales, and the vectors extracted by GNEMM perform best in the downstream retrieval and matching of various address types, which verifies its applicability in geographical named entity recommendation applications.https://www.mdpi.com/2220-9964/14/3/95geographical named entity matchingmulti-objectiveRetrieval-Augmented Generation (RAG)large language model (LLM)geographical named entity recommendation
spellingShingle Jiajun Zhang
Junjie Fang
Chengkun Zhang
Wei Zhang
Huanbing Ren
Liuchang Xu
Geographic Named Entity Matching and Evaluation Recommendation Using Multi-Objective Tasks: A Study Integrating a Large Language Model (LLM) and Retrieval-Augmented Generation (RAG)
ISPRS International Journal of Geo-Information
geographical named entity matching
multi-objective
Retrieval-Augmented Generation (RAG)
large language model (LLM)
geographical named entity recommendation
title Geographic Named Entity Matching and Evaluation Recommendation Using Multi-Objective Tasks: A Study Integrating a Large Language Model (LLM) and Retrieval-Augmented Generation (RAG)
title_full Geographic Named Entity Matching and Evaluation Recommendation Using Multi-Objective Tasks: A Study Integrating a Large Language Model (LLM) and Retrieval-Augmented Generation (RAG)
title_fullStr Geographic Named Entity Matching and Evaluation Recommendation Using Multi-Objective Tasks: A Study Integrating a Large Language Model (LLM) and Retrieval-Augmented Generation (RAG)
title_full_unstemmed Geographic Named Entity Matching and Evaluation Recommendation Using Multi-Objective Tasks: A Study Integrating a Large Language Model (LLM) and Retrieval-Augmented Generation (RAG)
title_short Geographic Named Entity Matching and Evaluation Recommendation Using Multi-Objective Tasks: A Study Integrating a Large Language Model (LLM) and Retrieval-Augmented Generation (RAG)
title_sort geographic named entity matching and evaluation recommendation using multi objective tasks a study integrating a large language model llm and retrieval augmented generation rag
topic geographical named entity matching
multi-objective
Retrieval-Augmented Generation (RAG)
large language model (LLM)
geographical named entity recommendation
url https://www.mdpi.com/2220-9964/14/3/95
work_keys_str_mv AT jiajunzhang geographicnamedentitymatchingandevaluationrecommendationusingmultiobjectivetasksastudyintegratingalargelanguagemodelllmandretrievalaugmentedgenerationrag
AT junjiefang geographicnamedentitymatchingandevaluationrecommendationusingmultiobjectivetasksastudyintegratingalargelanguagemodelllmandretrievalaugmentedgenerationrag
AT chengkunzhang geographicnamedentitymatchingandevaluationrecommendationusingmultiobjectivetasksastudyintegratingalargelanguagemodelllmandretrievalaugmentedgenerationrag
AT weizhang geographicnamedentitymatchingandevaluationrecommendationusingmultiobjectivetasksastudyintegratingalargelanguagemodelllmandretrievalaugmentedgenerationrag
AT huanbingren geographicnamedentitymatchingandevaluationrecommendationusingmultiobjectivetasksastudyintegratingalargelanguagemodelllmandretrievalaugmentedgenerationrag
AT liuchangxu geographicnamedentitymatchingandevaluationrecommendationusingmultiobjectivetasksastudyintegratingalargelanguagemodelllmandretrievalaugmentedgenerationrag