@inproceedings{zhang-etal-2025-srm,
title = "{SRM}-{LLM}: Semantic Relationship Mining with {LLM}s for Temporal Knowledge Graph Extrapolation",
author = "Zhang, Fu and
Zhang, Panfeng and
Cheng, Jingwei",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.868/",
doi = "10.18653/v1/2025.findings-emnlp.868",
pages = "16007--16021",
ISBN = "979-8-89176-335-7",
abstract = "Temporal knowledge graph (TKG) extrapolation aims to predict future facts by modeling the dynamic evolution of historical facts within TKGs. Existing methods often neglect the complex semantic relationships between relations when modeling their dynamic evolution, leading to incomplete relation representations and affecting the accuracy of reasoning. Inspired by the advancements in large language models (LLMs), we propose Semantic Relationship Mining based on LLMs (SRM-LLM), a novel approach for extracting semantic relationships to achieve TKG extrapolation. By leveraging LLMs to analyze the types of relations, we first identify several common relation types (e.g., causal, synonymous) in TKGs. We then design the LLM-based prompting strategy to capture latent semantic connections between relations, enabling the construction of relational association subgraphs for relation representation learning. In addition, SRM-LLM further enhances reasoning capabilities by incorporating structured logical constraints to guide inference. Experiments on five TKG datasets show significant performance gains and achieve new state of the art (SOTA) results, confirming the effectiveness of our method on TKG extrapolation tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-srm">
<titleInfo>
<title>SRM-LLM: Semantic Relationship Mining with LLMs for Temporal Knowledge Graph Extrapolation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Panfeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Temporal knowledge graph (TKG) extrapolation aims to predict future facts by modeling the dynamic evolution of historical facts within TKGs. Existing methods often neglect the complex semantic relationships between relations when modeling their dynamic evolution, leading to incomplete relation representations and affecting the accuracy of reasoning. Inspired by the advancements in large language models (LLMs), we propose Semantic Relationship Mining based on LLMs (SRM-LLM), a novel approach for extracting semantic relationships to achieve TKG extrapolation. By leveraging LLMs to analyze the types of relations, we first identify several common relation types (e.g., causal, synonymous) in TKGs. We then design the LLM-based prompting strategy to capture latent semantic connections between relations, enabling the construction of relational association subgraphs for relation representation learning. In addition, SRM-LLM further enhances reasoning capabilities by incorporating structured logical constraints to guide inference. Experiments on five TKG datasets show significant performance gains and achieve new state of the art (SOTA) results, confirming the effectiveness of our method on TKG extrapolation tasks.</abstract>
<identifier type="citekey">zhang-etal-2025-srm</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.868</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.868/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>16007</start>
<end>16021</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SRM-LLM: Semantic Relationship Mining with LLMs for Temporal Knowledge Graph Extrapolation
%A Zhang, Fu
%A Zhang, Panfeng
%A Cheng, Jingwei
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F zhang-etal-2025-srm
%X Temporal knowledge graph (TKG) extrapolation aims to predict future facts by modeling the dynamic evolution of historical facts within TKGs. Existing methods often neglect the complex semantic relationships between relations when modeling their dynamic evolution, leading to incomplete relation representations and affecting the accuracy of reasoning. Inspired by the advancements in large language models (LLMs), we propose Semantic Relationship Mining based on LLMs (SRM-LLM), a novel approach for extracting semantic relationships to achieve TKG extrapolation. By leveraging LLMs to analyze the types of relations, we first identify several common relation types (e.g., causal, synonymous) in TKGs. We then design the LLM-based prompting strategy to capture latent semantic connections between relations, enabling the construction of relational association subgraphs for relation representation learning. In addition, SRM-LLM further enhances reasoning capabilities by incorporating structured logical constraints to guide inference. Experiments on five TKG datasets show significant performance gains and achieve new state of the art (SOTA) results, confirming the effectiveness of our method on TKG extrapolation tasks.
%R 10.18653/v1/2025.findings-emnlp.868
%U https://aclanthology.org/2025.findings-emnlp.868/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.868
%P 16007-16021
Markdown (Informal)
[SRM-LLM: Semantic Relationship Mining with LLMs for Temporal Knowledge Graph Extrapolation](https://aclanthology.org/2025.findings-emnlp.868/) (Zhang et al., Findings 2025)
ACL