@inproceedings{huang-etal-2025-sce,
title = "{SCE}: Semantic Consistency Enhanced Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning",
author = "Huang, Yanwen and
Liu, Yao and
Liu, Qiao and
Hou, Rui and
Dai, Tingting",
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.289/",
pages = "5413--5425",
ISBN = "979-8-89176-335-7",
abstract = "Multi-hop reasoning with reinforcement learning has proven effective in discovering inference paths in incomplete knowledge graphs. However, a major challenge remains: spurious paths (incorrect reasoning paths that accidentally lead to correct answers) often arise due to reward mechanisms that prioritize final results over reasoning quality. While existing approaches attempt to mitigate this issue using external rules, they often neglect the internal semantic consistency between the target triple and the intermediate triples along the reasoning path. In this paper, we propose a novel framework, $\textbf{S}$emantic $\textbf{C}$onsistency $\textbf{E}$nhanced Reinforcement Learning (SCE), which incorporates semantic consistency into the reward function to guide multi-hop reasoning. Experimental results demonstrate that SCE outperforms strong baseline methods and facilitates the discovery of more interpretable reasoning paths."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2025-sce">
<titleInfo>
<title>SCE: Semantic Consistency Enhanced Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanwen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingting</namePart>
<namePart type="family">Dai</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>Multi-hop reasoning with reinforcement learning has proven effective in discovering inference paths in incomplete knowledge graphs. However, a major challenge remains: spurious paths (incorrect reasoning paths that accidentally lead to correct answers) often arise due to reward mechanisms that prioritize final results over reasoning quality. While existing approaches attempt to mitigate this issue using external rules, they often neglect the internal semantic consistency between the target triple and the intermediate triples along the reasoning path. In this paper, we propose a novel framework, Semantic Consistency Enhanced Reinforcement Learning (SCE), which incorporates semantic consistency into the reward function to guide multi-hop reasoning. Experimental results demonstrate that SCE outperforms strong baseline methods and facilitates the discovery of more interpretable reasoning paths.</abstract>
<identifier type="citekey">huang-etal-2025-sce</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.289/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>5413</start>
<end>5425</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCE: Semantic Consistency Enhanced Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning
%A Huang, Yanwen
%A Liu, Yao
%A Liu, Qiao
%A Hou, Rui
%A Dai, Tingting
%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 huang-etal-2025-sce
%X Multi-hop reasoning with reinforcement learning has proven effective in discovering inference paths in incomplete knowledge graphs. However, a major challenge remains: spurious paths (incorrect reasoning paths that accidentally lead to correct answers) often arise due to reward mechanisms that prioritize final results over reasoning quality. While existing approaches attempt to mitigate this issue using external rules, they often neglect the internal semantic consistency between the target triple and the intermediate triples along the reasoning path. In this paper, we propose a novel framework, Semantic Consistency Enhanced Reinforcement Learning (SCE), which incorporates semantic consistency into the reward function to guide multi-hop reasoning. Experimental results demonstrate that SCE outperforms strong baseline methods and facilitates the discovery of more interpretable reasoning paths.
%U https://aclanthology.org/2025.findings-emnlp.289/
%P 5413-5425
Markdown (Informal)
[SCE: Semantic Consistency Enhanced Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning](https://aclanthology.org/2025.findings-emnlp.289/) (Huang et al., Findings 2025)
ACL