Yuying Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuying Liu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Bin Zhou
National university of defense technology, Changsha, China
2 shared publications - Liqun Gao
National university of defense technology, Changsha, China
2 shared publications - Xin Song
National University of Defense Technology, Changsha, Hunan, China
2 shared publications - Ye Wang
Harbin Institute of Technology
2 shared publications Bin Zhou
1 shared publication- Bin Zhou
National University of Defense Technology
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4357-4368
FlowPath: From Discrete Paths to Continuous Semantic Flows for Knowledge Graph Completion
Knowledge graph completion (KGC) aims to infer missing facts based on existing triplets. Traditional path-based methods formulate reasoning as a discrete multi-hop traversal, which suffers from exponential search space and error accumulation.In this paper, we propose FlowPath, which rethinks the reasoning process by transforming discrete symbolic paths into a continuous semantic flow in the latent space. Specifically, we formalize the inference from a head entity to the target tail entity as an Ordinary Differential Equation (ODE) governed by a relation-conditioned neural velocity field, which learns to steer a smooth and expressive semantic transformation along the reasoning trajectory. To prevent the continuous flow from drifting into invalid semantic regions, we further introduce a structure-anchored guidance mechanism that leverages factual multi-hop paths from the knowledge graph as topological constraints, grounding the learned flow in the discrete relational structure. Moreover, a uncertainty weighting strategy is employed to adaptively balance the joint optimization of link prediction, flow generation, and structural guidance. By bridging discrete symbolic paths and continuous neural dynamics, FlowPath inherits the interpretability of path-based reasoning while possessing the flexibility and expressiveness of generative modeling. Extensive experiments on benchmark datasets demonstrate that FlowPath achieves competitive performance, and additional analysis confirms the effectiveness of modeling the reasoning paths of KGC as a continuous semantic flow.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4357-4368
Open AccessFlowPath: From Discrete Paths to Continuous Semantic Flows for Knowledge Graph Completion
Knowledge graph completion (KGC) aims to infer missing facts based on existing triplets. Traditional path-based methods formulate reasoning as a discrete multi-hop traversal, which suffers from exponential search space and error accumulation.In this paper, we propose FlowPath, which rethinks the reasoning process by transforming discrete symbolic paths into a continuous semantic flow in the latent space. Specifically, we formalize the inference from a head entity to the target tail entity as an Ordinary Differential Equation (ODE) governed by a relation-conditioned neural velocity field, which learns to steer a smooth and expressive semantic transformation along the reasoning trajectory. To prevent the continuous flow from drifting into invalid semantic regions, we further introduce a structure-anchored guidance mechanism that leverages factual multi-hop paths from the knowledge graph as topological constraints, grounding the learned flow in the discrete relational structure. Moreover, a uncertainty weighting strategy is employed to adaptively balance the joint optimization of link prediction, flow generation, and structural guidance. By bridging discrete symbolic paths and continuous neural dynamics, FlowPath inherits the interpretability of path-based reasoning while possessing the flexibility and expressiveness of generative modeling. Extensive experiments on benchmark datasets demonstrate that FlowPath achieves competitive performance, and additional analysis confirms the effectiveness of modeling the reasoning paths of KGC as a continuous semantic flow.
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 728-737
Robust Multi-modal Knowledge Graph Completion via Modality-Specific Experts
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 728-737
Open AccessRobust Multi-modal Knowledge Graph Completion via Modality-Specific Experts
- 21 April 2026
- Published by Elsevier in Information Processing & Management
- Vol. 63 (7)
Unified Generative Intent Discovery: Bridging in-domain classification and open-world intent generation
- 21 April 2026
- Published by Elsevier in Information Processing & Management
- Vol. 63 (7)
Unified Generative Intent Discovery: Bridging in-domain classification and open-world intent generation
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 996-1006
KnowFC: Navigating Knowledge Conflicts in Large Language Model-based Fact-Checking
When fact-checking methods based on large language models (LLMs) use external evidence to validate claims, knowledge conflicts often arise. These conflicts typically stem from inconsistencies between the external evidence and LLMs' internal pre-existing knowledge. Such an inconsistency could lead LLMs to draw incorrect answers when validating claims, especially when they are overly confident in their internal incorrect knowledge. Previous works on LLM-based fact-checking have overlooked this issue. This paper, for the first time, proposes a framework (namely KnowFC) to navigate this issue. Our key insight is dividing and adaptively utilizing the knowledge that LLMs know and do not know, thereby avoiding conflicts while enhancing the correctness and efficiency of fact-checking. Specifically, in KnowFC, we propose an adaptive retrieval method, where we train an LLM using a reinforcement learning algorithm coupled with the Dunning-Kruger effect-inspired reward mechanism to identify its knowledge boundaries through confidence calibration, thereby realizing adaptive evidence retrieval. Besides, we propose a reliable and debiased fact verification method, where we organize and construct reasoning graphs using retrieved evidence to verify claims, followed by a causal intervention method using causal mediation analysis to mitigate internal knowledge interference. Experimental results on both FEVEROUS and AVeriTeC datasets show that our method outperforms baseline methods in terms of accuracy and F1 score, while also improving fact-checking efficiency.
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 996-1006
Open AccessKnowFC: Navigating Knowledge Conflicts in Large Language Model-based Fact-Checking
When fact-checking methods based on large language models (LLMs) use external evidence to validate claims, knowledge conflicts often arise. These conflicts typically stem from inconsistencies between the external evidence and LLMs' internal pre-existing knowledge. Such an inconsistency could lead LLMs to draw incorrect answers when validating claims, especially when they are overly confident in their internal incorrect knowledge. Previous works on LLM-based fact-checking have overlooked this issue. This paper, for the first time, proposes a framework (namely KnowFC) to navigate this issue. Our key insight is dividing and adaptively utilizing the knowledge that LLMs know and do not know, thereby avoiding conflicts while enhancing the correctness and efficiency of fact-checking. Specifically, in KnowFC, we propose an adaptive retrieval method, where we train an LLM using a reinforcement learning algorithm coupled with the Dunning-Kruger effect-inspired reward mechanism to identify its knowledge boundaries through confidence calibration, thereby realizing adaptive evidence retrieval. Besides, we propose a reliable and debiased fact verification method, where we organize and construct reasoning graphs using retrieved evidence to verify claims, followed by a causal intervention method using causal mediation analysis to mitigate internal knowledge interference. Experimental results on both FEVEROUS and AVeriTeC datasets show that our method outperforms baseline methods in terms of accuracy and F1 score, while also improving fact-checking efficiency.
- 10 March 2023
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 67 (1) , 362-375
A New Method for Identifying Influential Spreaders in Complex Networks
Social networks have an important role in the distribution of ideas. With the rapid development of the social networks, identifying the influential nodes provides a chance to turn the new potential of global information spread into reality. The measurement of the spreading capabilities of nodes is an attractive challenge in social networks analysis. In this paper, a novel method is proposed to identify the influential nodes in complex networks. The proposed method determines the spreading capability of a node based on its local and global positions. The degree centrality is improved by the Shannon entropy to measure the local influence of nodes. The k-shell method is improved by the clustering coefficient to measure the global influence of nodes. To rank the importance of nodes, the entropy weighting method is used to calculate the weight for the local and global influences. The Vlsekriterijumska Optimizacija I Kompromisno Resenje method is used to integrate the local and global influences of a node and obtain its importance. The experiments are conducted on 13 real-world networks to evaluate the performance of the proposed method. The experimental results show that the proposed method is more powerful and accurate to identify influential nodes than other methods.
- 10 March 2023
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 67 (1) , 362-375
A New Method for Identifying Influential Spreaders in Complex Networks
Social networks have an important role in the distribution of ideas. With the rapid development of the social networks, identifying the influential nodes provides a chance to turn the new potential of global information spread into reality. The measurement of the spreading capabilities of nodes is an attractive challenge in social networks analysis. In this paper, a novel method is proposed to identify the influential nodes in complex networks. The proposed method determines the spreading capability of a node based on its local and global positions. The degree centrality is improved by the Shannon entropy to measure the local influence of nodes. The k-shell method is improved by the clustering coefficient to measure the global influence of nodes. To rank the importance of nodes, the entropy weighting method is used to calculate the weight for the local and global influences. The Vlsekriterijumska Optimizacija I Kompromisno Resenje method is used to integrate the local and global influences of a node and obtain its importance. The experiments are conducted on 13 real-world networks to evaluate the performance of the proposed method. The experimental results show that the proposed method is more powerful and accurate to identify influential nodes than other methods.