The DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Reasoning Over Semantic-Level Graph for Fact Checking
Open accessAbstract
Fact checking is a challenging task because verifying the truthfulness of a claim requires reasoning about multiple retrievable evidence.In this work, we present a method suitable for reasoning about the semantic-level structure of evidence.Unlike most previous works, which typically represent evidence sentences with either string concatenation or fusing the features of isolated evidence sentences, our approach operates on rich semantic structures of evidence obtained by semantic role labeling.We propose two mechanisms to exploit the structure of evidence while leveraging the advances of pre-trained models like BERT, GPT or XLNet.Specifically, using XLNet as the backbone, we first utilize the graph structure to re-define the relative distances of words, with the intuition that semantically related words should have short distances.Then, we adopt graph convolutional network and graph attention network to propagate and aggregate information from neighboring nodes on the graph.We evaluate our system on FEVER, a benchmark dataset for fact checking, and find that rich structural information is helpful and both our graph-based mechanisms improve the accuracy.Our model is the state-of-the-art system in terms of both official evaluation metrics, namely claim verification accuracy and FEVER score.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Existing fact-verification approaches follow a multi-stage pipeline of claim detection, evidence retrieval and verdict prediction (Guo et al., 2022; Zhong et al., 2020). Such methods, however, require access to external databases and can have considerable inference costs.”
From SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models (2023) · cites this paper as Zhong et al., 2020
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Semi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853
Graph Attention NetworksPreprint
Veličković, P., Casanova, A., Liò, P., Cucurull, G., Romero, A., & Bengio, Y. (2017) · arXiv (Cornell University) · doi:10.17863/cam.48429 · Cited by 19,745
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2017) · arXiv · doi:10.48550/arxiv.1710.10903 · Cited by 12,107
The spread of true and false news online
Vosoughi, S., Roy, D., & Aral, S. (2018) · Science · doi:10.1126/science.aap9559 · Cited by 8,847 · cited 1×
“Vosoughi et al. (2018) show that false news reaches more people than the truth.”
BackgroundXLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687
Open Information Extraction from the Web
Etzioni, O., Banko, M., Cafarella, M. J., Soderland, S., & Weld, D. S. (2007) · CACM · doi:10.1145/1409360.1409378 · Cited by 2,620
Flagged first, then by citations
Cited by
Sorted by citations
Items 101–161 of 161
A Semantics-Aware Approach to Automated Claim Verification
Figueras, B. C., Oller, M., & Agerri, R. (2022) · Fact Extraction and VERification Workshop (FEVER) · doi:10.18653/v1/2022.fever-1.5 · Cited by 4
Evidence-Based Document-Level Event Factuality Identification
Zhang, H., Zhong, Q., Li, P., & Zhu, X. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20865-2_18 · Cited by 4
Constrained Fact Verification for FEVER
Pratapa, A., Jayanthi, S. M., & Nerella, K. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.629 · Cited by 5
Modeling Entity Knowledge for Fact Verification
Liu, Y., Zhu, C., & Zeng, M. (2021) · Fact Extraction and VERification Workshop (FEVER) · doi:10.18653/v1/2021.fever-1.6 · Cited by 5
Top Ten Challenges Towards Agentic Neural Graph DatabasesPreprint
Bai, J., Wang, Z., Zhou, Y., Yin, H., Fei, W., Hu, Q., Deng, Z., Cheng, J., Zheng, T., Tsang, H. T., et al. (2025) · Qeios · doi:10.32388/v8qvha · Cited by 19
Concept-enhanced heterogeneous graph network for fact verification
Chen, Z., Liao, L., Hui, S. C., & Huang, H. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107959 · Cited by 3
Vallayil, M., Nand, P., Yan, W., Allende‐Cid, H., & Vamathevan, T. (2025) · Applied Sciences · doi:10.3390/app15041970 · Cited by 3
Zheng, L., Li, C., Jia, H., & Zhang, X. (2025) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc67331.2025.00053 · Cited by 5
Heterogeneous-Graph Reasoning and Fine-Grained Aggregation for Fact Checking
Lin, H., & Fu, X. (2022) · Fact Extraction and VERification Workshop (FEVER) · doi:10.18653/v1/2022.fever-1.2 · Cited by 3
Enhancing Information Retrieval in Fact Extraction and Verification
Olivares, D. G., Quijano-Sánchez, L., & Liberatore, F. (2023) · Fact Extraction and VERification Workshop (FEVER) · doi:10.18653/v1/2023.fever-1.4 · Cited by 4
Multi-view Hierarchical Graph Neural Network for Argumentation Mining
Sun, Y., Bao, J., Tu, G., Liang, B., Yang, M., & Xu, R. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10391-0 · Cited by 5
Semantic processing for Urdu: corpus creation, parsing, and generation
Amin, M. S., Zhang, X., Luca Anselma, A., Mazzei, A., & Bos, J. (2025) · Language Resources and Evaluation · doi:10.1007/s10579-025-09819-2 · Cited by 4
Roberts, D. A. O. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72240-1_36 · Cited by 4
HiGIL: Hierarchical Graph Inference Learning for Fact Checking
Mao, Q., Wang, Y., Yang, C., Du, L., Peng, H. M., Wu, J. X., Li, J., & Wang, Z. (2022) · Proceedings · doi:10.1109/icdm54844.2022.00043 · Cited by 3
A syntactic multi-level interaction network for rumor detection
Chen, Z., Zhuang, F., Liao, L., Jia, M., Li, J., & Huang, H. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09140-5 · Cited by 3
Understanding the Impact of Evidence-Aware Sentence Selection for Fact Checking
Bekoulis, G., Papagiannopoulou, C., & Deligiannis, N. (2021) · Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda (NLP4IF) · doi:10.18653/v1/2021.nlp4if-1.4 · Cited by 3
Fact Extraction and VERification -- The FEVER case: An OverviewPreprint
Bekoulis, G., Papagiannopoulou, C., & Deligiannis, N. (2020) · arXiv (Cornell University) · Cited by 3
Advancing Vietnamese Fact Extraction and Verification through Multi-Stage Text Ranking
Tran, Q.-D., Tran, T.-H., & Tran, K. Q. (2024) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr63514.2024.10660734 · Cited by 2
Santra, P., Ghosh, M., Ganguly, D., Basuchowdhuri, P., & Naskar, S. K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-68323-7_34 · Cited by 2
Liu, S., Li, C., Zhang, X., Zhao, M., Xu, Y., & Bu, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681639 · Cited by 2
Towards Better Evidence Extraction Methods for Fact-Checking Systems
Azevedo, P., Rocha, G., Esteves, D., & Cardoso, H. L. (2021) · IEEE/WIC/ACM International Conference on Web Intelligence · doi:10.1145/3486622.3493930 · Cited by 3
Leveraging Diversity-Aware Context Attention Networks for Fake News Detection on Social Platforms
Chen, Z., Wu, P., & Li, P. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892488 · Cited by 2
Knowledge-Enhanced Graph Attention Network for Fact Verification
Chen, C., Zheng, J., & Chen, H. (2021) · Mathematics · doi:10.3390/math9161949 · Cited by 2
Cross-Document Fact Verification Based on Evidential Graph Attention Network
Xu, X., Zhong, Q., Liu, C., Zhu, X., & Li, P. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650990 · Cited by 1
An enhanced dynamic interaction network for claim verification
Li, P., Sun, X., Yu, H., Zhang, W., & Xu, G. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.12.112 · Cited by 1
Vietnamese Fact Checking based on the Knowledge Graph and Deep Learning
Duong, H. T., Ho, V., & Do, P. (2022) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf55975.2022.10013889 · Cited by 1
Adversarial Performance Evaluation and Analysis on Recent Strong Models for Fact Verification
Wang, H., Li, Y., & Dou, Y. (2022) · International Conference on Cloud Computing, Big Data and Internet of Things (3CBIT) · doi:10.1109/3cbit57391.2022.00022 · Cited by 1
Scudo, F. L. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-31469-8_2 · Cited by 1
Decoupled User Preference Enhanced Fake News Detection
Liu, H. (2024) · International Conference on Cyber Security, Artificial Intelligence and Digital Economy (CSAIDE) · doi:10.1145/3672919.3672931 · Cited by 1
Wang, Y., Kang, X., & Li, T. (2024) · IEEE Access · doi:10.1109/access.2024.3439689 · Cited by 1
Duong, H. T., Ho, V., & Do, P. (2024) · IEEE Access · doi:10.1109/access.2024.3523416 · Cited by 1
Hidden Biases in Unreliable News Detection DatasetsPreprint
Zhou, X., Elfardy, H., Christodoulopoulos, C., Butler, T., & Bansal, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.10130 · Cited by 1
Graph Attention and Interaction Network With Multi-Task Learning for Fact Verification
Yang, R., Wang, R., & Ling, Z.-H. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414889
Natural language processing on noisy text
Dong, R. (2021) · doi:10.17760/d20416553
CNGT: Co-attention Networks with Graph Transformer for Fact Verification
Yuan, J., Chen, C., Hou, C., & Yuan, X. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-46664-9_39
Tabular reasoning via two-stage knowledge injection
Shi, Q., Yu, Z., Qi, L., & Liu, T. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-02073-4
Toward complex data structure aggregation and truth discovery
Sabetpour, N. (2022) · doi:10.31274/td-20240329-813
ÇİZGE ÖĞRENMEDE ÇİZGE SİNİR AĞLARI
Gümüş, H. T., & Eyüpoğlu, C. (2024) · İstanbul Ticaret Üniversitesi Teknoloji ve Uygulamalı Bilimler Dergisi · doi:10.56809/icujtas.1442504
Claim polarity analysis from conflicting sources
Senouci, A., Meziane, H., & Benbernou, S. (2024) · International Journal of Data Science and Analytics · doi:10.1007/s41060-024-00634-6
Factify: An Automated Fact-Checker for Web Information
Adesokan, A., & Elbassuoni, S. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825147
A Study of Graph Neural Network Frameworks and Frontiers
Gunasundari, C., & Antonysamy, B. (2025) · Information systems engineering and management · doi:10.1007/978-3-031-90478-3_5
KQFV: a knowledge-enhanced method using question answering for fact verification
Bian, Y., & Ma, T. (2025) · Journal of Intelligent Information Systems · doi:10.1007/s10844-025-00956-2
Systematic Approaches to Fact Verification: Evidence Retrieval, Veracity Prediction, and Beyond
Wu, Z., Sun, N., Jiang, J., & Yang, S. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8183-9_22
Deep One-Directional Neural Semantic Siamese Network for High-Accuracy Fact Verification
Naseer, M., Windiatmaja, J. H., Asvial, M., & Sari, R. F. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9070172
3. Automated Fact Verification: Lessons Learned from Participating in the FEVER Challenge
Kruengkrai, C., & Yamagishi, J. (2022) · The Journal of The Institute of Image Information and Television Engineers · doi:10.3169/itej.76.440
EVOCA: Explainable Verification of Claims by Graph Alignment
Felice, C. D., Longo, F., Mongiovı̀, M., Santamaria, D. F., & Tuccari, G. G. (2025) · Information · doi:10.3390/info16070597
Learning to mine all minimal evidences for unverified claims
Liu, Y., Wan, H., Du, J., Wang, Y., Qi, K., & Luo, W. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122505
Building A Wikipedia-Based Hindi Fact Verification System
Nagar, S. (2025) · INTERNATIONAL JOURNAL OF RESEARCH AND ANALYTICAL REVIEWS · doi:10.56975/ijrar.v12i3.318929
Dual-View Evidence Learning and Cross-View Fusion for Enhanced Text-Table Fact Verification
Wu, Z., Jiang, J., Yang, S., & Sun, N. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342923
STRIVE: Structured Reasoning for Self-improvement in Claim Verification
Gong, H., Li, J., Wu, J., Liu, Q., & Wu, S. (2026) · Machine Intelligence Research · doi:10.1007/s11633-025-1598-5 · Cited by 4
Wu, Z., Yang, Z., Jiang, J., Yang, S., & Sun, N. (2026) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3773966.3777966
EDITMEM: Enhancing Multi-Hop Fact Verification Via Editable Memory
Lan, Y., Liu, Z. B., Gu, Y., & Yu, G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463827
Evaluating the Novelty of Information
Azaria, B., Hirschprung, R. S., & Alkoby, S. (2026) · International Journal on Semantic Web and Information Systems · doi:10.4018/ijswis.407997
Triple-R: Iterative Query Rewriting and Refinement for Retrieval-Augmented Fake News Detection
Li, J., Wang, J., Hu, L., & Deng, Y. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792246
Self-citationToward effective Text-to-MongoDB query translation
Aggoune, A. (2026) · International Journal of Advances in Intelligent Informatics · doi:10.26555/ijain.v12i2.2360
SEAR: Structured entity alignment reasoning for agricultural rumor detection
Xiong, S., Si, Y., Hou, Y., Li, Y., Wang, Z., & Si, H. (2026) · Information Sciences · doi:10.1016/j.ins.2026.123985
Yan, Z., Jiang, Z., Ma, C., Dong, F., Tong, Z., & Lin, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-42929-2_18
The F1 Mirage: Unmasking Shortcut Learning in Mistral’s Fact-Checking
Kaur, G., Badache, I., & Yacoub, A. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.09.504
Metadata
- Authors
- Zhong, W., Xu, J., Tang, D., Xu, Z., Duan, N., Zhou, M., Wang, J., & Yin, J.
- Affiliations
- Sun Yat-sen University (CN)
- Peking University (CN)
- Microsoft (United States) (US)
- Venue
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Published
- 2020
- Pages
- 6170-6180
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W3034808961
- Cited by
- 151
- References
- 36
- Citations by year
- 2026: 4 · 2025: 15 · 2024: 22 · 2023: 26 · 2022: 36 · 2021: 38 · 2020: 10
- FWCI
- 58.32
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Funders
- National Natural Science Foundation of China (U1611264, U1711262, U1811261, U1811264, U1711261, U1911203)
- Basic and Applied Basic Research Foundation of Guangdong Province (2019B15 15130001)
- Topics
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- fact-checking, claim verification, semantic role labeling, graph convolutional networks, graph attention networks, XLNet, FEVER dataset, word distance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
