Elamur Research⌕
☰
home / papers / 2026 / SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking

SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking

Paper · 2026 · Dien X. Tran, Nam V. Nguyen, Tran Tan Thanh et al.

Summary

Automated fact-checking for Vietnamese, a low-resource language, is hard for two reasons. Source documents are often far longer than BERT-style encoders can read, and keyword retrieval fails on paraphrase and ambiguity. The authors present SemViQA, which labels a claim as Supported, Refuted or NEI and also locates the supporting evidence sentence in the context. Long contexts are split at sentence boundaries into chunks of roughly 400 tokens. In the Semantic-based Evidence Retrieval (SER) stage, fast TF-IDF ranks candidate sentences. Only low-confidence cases go to QATC, a question-answering model trained with an additional per-token binary evidence-tagging objective. Two-step Verdict Classification (TVC) then combines a three-class classifier with a binary one, which makes the system more robust to label imbalance. SemViQA reaches state-of-the-art strict accuracy on ISE-DSC01 and ViWikiFC and won the UIT Data Science Challenge. It also runs far faster than LLM-based alternatives. This makes it a practical, reproducible baseline for fact verification in other low-resource languages.

Key points

  • Strict accuracy: 78.97% on ISE-DSC01 and 80.82% on ViWikiFC. On the ISE-DSC01 private leaderboard it ranked 1st, ahead of DS@UIT Dynasty (78.05). Its verdict accuracy (82.54) was below that team's 84.76.
  • QATC training: tokens inside evidence sentences are labeled 1 and all other tokens 0; for NEI claims every token is 0. The model uses a sigmoid feed-forward head trained with BCE loss.
  • Speed: a full ISE-DSC01 run takes about 5,200 s, compared with over 31,000 s for Qwen2.5-3B-Instruct and 9,800 s for ViMRC large. SemViQA Faster batches the sub-contexts in parallel for up to 7× faster inference, with only a small loss in accuracy.
  • Long-context benefit: ISE-DSC01 contexts can exceed 4,800 tokens, which is where SER helps most. On ViWikiFC (about 512 tokens on average), adding SER still raises evidence retrieval accuracy by 1.86%.
  • Limitations and availability: the confidence thresholds that route hard cases to QATC are set by hand, and TVC adds extra inference cost. Code is available at github.com/DAVID-NGUYEN-S16/SemViQA.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Vietnam National University Ho Chi Minh CityHo Chi Minh City · Vietnam21 works · 14 citations🎓Ho Chi Minh City University of ScienceHo Chi Minh City · Vietnam5 works · 2 citations

Also on the byline: Industrial University of Ho Chi Minh City.

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksSocial Sciences · 1,772 worksSociology and Political Science · 577 works

🧭 Topics 1Research subjects and languages the work is about.Question answering · 441 works

Cite

Cite as Dien X. Tran, Nam V. Nguyen, Tran Tan Thanh, Anh T. Hoang, Dương Văn Tài, Lê Thanh Di and Phuc-Lu Le. 2026. SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-industry.94

@inproceedings{tran2026semviqa,
  title = {{SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking}},
  author = {Dien X. Tran, Nam V. Nguyen, Tran Tan Thanh, Anh T. Hoang, Dương Văn Tài, Lê Thanh Di and Phuc-Lu Le},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-industry.94},
  url = {https://doi.org/10.18653/v1/2026.acl-industry.94}
}

References

53 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Marah Abdin, Sam Ade Jacobs, Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat Behl, and 1 others. 2024. Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219.
  2. Rami Aly, Zhijiang Guo, Michael Sejr Schlichtkrull, James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Oana Cocarascu, and Arpit Mittal. 2021. The fact extraction and VERification over unstructured and structured information (FEVEROUS) shared task. In Proceedings of the Fourth Workshop on F…
  3. Rami Aly and Andreas Vlachos. 2022. Natural logic-guided autoregressive multi-hop document retrieval for fact verification. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6123–6135, Abu Dhabi, United Arab Emirates. Association for Computational Lingu… find
  4. Akari Asai, Zeqiu Wu, Yizhong Wang, Avi Sil, and Hannaneh Hajishirzi. 2024. Self-rag: Learning to retrieve, generate, and critique through self-reflection.
  5. In International Conference on Learning Representations, volume 2024, pages 9112–9141. find
  6. Pedro Azevedo, Gil Rocha, Diego Esteves, and Henrique Lopes Cardoso. 2022. Towards better evidence extraction methods for fact-checking systems. In IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT ’21, page 277–284, New York, NY, USA. Association for… find
  7. Zewen Chi, Li Dong, Furu Wei, Nan Yang, Saksham Singhal, Wenhui Wang, Xia Song, Xian-Ling Mao, Heyan Huang, and Ming Zhou. 2021. InfoXLM: An information-theoretic framework for cross-lingual language model pre-training. In Proceedings of the 2021 Conference of the North American Chapter of the Assoc…
  8. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association fo… find
  9. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, and 1 others. 2024. Deepseek-v3 technical report. Preprint, arXiv:2412.19437. find
  10. Mitchell DeHaven and Stephen Scott. 2023. BEVERS: A general, simple, and performant framework for automatic fact verification. In Proceedings of the Sixth Fact Extraction and VERification Workshop (FEVER), pages 58–65, Dubrovnik, Croatia. Association for Computational Linguistics. find
  11. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
  12. Huong T. Duong, Van H. Ho, and Phuc Do. 2023. Fact-checking vietnamese information using knowledge graph, datalog, and kg-bert. ACM Trans. Asian Low-Resour. Lang. Inf. Process., 22(10). find
  13. Mudasir A Ganaie, Minghui Hu, Ashwani Kumar Malik, Muhammad Tanveer, and Ponnuthurai N Suganthan. 2022. Ensemble deep learning: A review. Engineering Applications of Artificial Intelligence, 115:105151. find
  14. Alex Graves and Jürgen Schmidhuber. 2005. Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural networks : the official journal of the International Neural Network Society, 18:602–10. find
  15. Tetyana Hannichenko, Peter Bidyuk, Irina Kalinina, and Oleksandr Zhebko. 2023. Classification system based on ensemble methods for solving machine learning tasks. find
  16. Tran Thai Hoa, Tran Quang Duy, Khanh Quoc Tran, and Kiet Van Nguyen. 2025. Vifactcheck: a new benchmark dataset and methods for multi-domain news fact-checking in vietnamese. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative App… find
  17. Siqing Huo, Negar Arabzadeh, and Charles Clarke. 2023. Retrieving supporting evidence for generative question answering. In Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, SIGIR-AP ’23, page 11–20. ACM. find
  18. Zhengbao Jiang, Frank Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. Active retrieval augmented generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7969–7992, Singapore. Association fo…
  19. Ying Ju, Fubang Zhao, Shijie Chen, Bowen Zheng, Xuefeng Yang, and Yunfeng Liu. 2019. Technical report on conversational question answering. Preprint, arXiv:1909.10772. — [arXiv:1909.10772](https://arxiv.org/abs/1909.10772) find
  20. Mohammed Abdul Khaliq, Paul Yu-Chun Chang, Mingyang Ma, Bernhard Pflugfelder, and Filip Miletić. 2024. RAGAR, your falsehood radar: RAG-augmented reasoning for political fact-checking using multimodal large language models. In Proceedings of the Seventh Fact Extraction and VERification Workshop (FE… find
  21. Hung Tuan Le, Long Truong To, Manh Trong Nguyen, and Kiet Van Nguyen. 2024. Viwikifc: Fact-checking for vietnamese wikipedia-based textual knowledge source. Preprint, arXiv:2405.07615. find
  22. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. In Proceedings of the 34th Internation…
  23. Kun Li. 2021. Haha at fakedes 2021: A fake news detection method based on tf-idf and ensemble machine learning. In IberLEF@ SEPLN, pages 630–638. find
  24. Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2018. Focal loss for dense object detection. Preprint, arXiv:1708.02002.
  25. Ying-Jia Lin, Chun-Yi Lin, Chia-Jen Yeh, Yi-Ting Li, Yun-Yu Hu, Chih-Hao Hsu, Mei-Feng Lee, and Hung-Yu Kao. 2024. Cfever: A chinese fact extraction and verification dataset. Preprint, arXiv:2402.13025. — [arXiv:2402.13025](https://arxiv.org/abs/2402.13025) find
  26. Yichen Liu, Abhijit Dasgupta, and Qiwei He. 2024. Music genre classification: Ensemble learning with subcomponents-level attention. Preprint, arXiv:2412.15602. — [arXiv:2412.15602](https://arxiv.org/abs/2412.15602) find
  27. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. Preprint, arXiv:1907.11692.
  28. Nhi Ngoc Phuong Luong, Anh Thi Lan Le, Tin Van Huynh, Kiet Van Nguyen, and Ngan Nguyen. 2025. ViNumFCR: A novel Vietnamese benchmark for numerical reasoning fact checking on social media news. In Proceedings of the 18th International Natural Language Generation Conference, pages 134–147, Hanoi, Viet… find
  29. Christopher Malon. 2018. Team papelo: Transformer networks at FEVER. In Proceedings of the First Workshop on Fact Extraction and VERification (FEVER), pages 109–113, Brussels, Belgium. Association for Computational Linguistics. find
  30. Shrikant Malviya and Stamos Katsigiannis. 2024. Evidence retrieval for fact verification using multi-stage reranking. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7295– 7308, Miami, Florida, USA. Association for Computational Linguistics. find
  31. Yixin Nie, Haonan Chen, and Mohit Bansal. 2018. Combining fact extraction and verification with neural semantic matching networks. Preprint, arXiv:1811.07039. find
  32. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, and 1 others. 2024. Gpt-4 technical report. Preprint, arXiv:2303.08774.
  33. Xuan Ouyang, Shuohuan Wang, Chao Pang, Yu Sun, Hao Tian, Hua Wu, and Haifeng Wang. 2021. ERNIE-M: Enhanced multilingual representation by aligning cross-lingual semantics with monolingual corpora. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 27–38,…
  34. Shahzad Qaiser and Ramsha Ali. 2018. Text mining: Use of tf-idf to examine the relevance of words to documents. International Journal of Computer Applications, 181. find
  35. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. find
  36. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2024. Qwen2.5 technical report. Preprint, arXiv:2412.15115. find
  37. Aniketh Janardhan Reddy, Gil Rocha, and Diego Esteves. 2018. Defactonlp: Fact verification using entity recognition, tfidf vector comparison and decomposable attention. arXiv preprint arXiv:1809.00509. find
  38. Nils Reimers and Iryna Gurevych. 2019a. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992,…
  39. Nils Reimers and Iryna Gurevych. 2019b. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992,…
  40. Tobias Schimanski, Jingwei Ni, Mathias Kraus, Elliott Ash, and Markus Leippold. 2024. Towards faithful and robust LLM specialists for evidence-based question-answering. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1913– 193… find
  41. Vinay Setty. 2024. Surprising efficacy of fine-tuned transformers for fact-checking over larger language models. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’24, page 2842–2846, New York, NY, USA. Association for Computing… find
  42. Amir Soleimani, Christof Monz, and Marcel Worring. 2020. Bert for evidence retrieval and claim verification. In Advances in Information Retrieval: 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, April 14–17, 2020, Proceedings, Part II, page 359–366, Berlin, Heidelberg. Springer… find
  43. Weihang Su, Yichen Tang, Qingyao Ai, Zhijing Wu, and Yiqun Liu. 2024. DRAGIN: Dynamic retrieval augmented generation based on the real-time information needs of large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),…
  44. Gemini Team, Rohan Anil, Sebastian Borgeaud, and 1 others. 2024. Gemini: A family of highly capable multimodal models. Preprint, arXiv:2312.11805.
  45. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vo…
  46. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. Preprint…
  47. Bao Tran, T. N. Khanh, Khang Nguyen Tuong, Thien Dang, Quang Nguyen, Nguyen T. Thinh, and Vo T. Hung. 2024a. BERT-Based Model for Vietnamese Fact Verification Dataset, page 219–231. Springer Nature Switzerland. find
  48. Quang-Duy Tran, Thai-Hoa Tran, and Khanh Quoc Tran. 2024b. Advancing vietnamese fact extraction and verification through multi-stage text ranking. In 2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR), pages 1–7. find
  49. Guangtao Wang, Qinbao Song, and Xiaoyan Zhu. 2021. Ensemble learning based classification algorithm recommendation. Preprint, arXiv:2101.05993. — [arXiv:2101.05993](https://arxiv.org/abs/2101.05993) find
  50. Moy Yuan and Andreas Vlachos. 2024. Zero-shot fact-checking with semantic triples and knowledge graphs. In Proceedings of the 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024), pages 105–115, Bangkok, Thailand. Association for Computational Linguistics. find
  51. Liwen Zheng, Chaozhuo Li, Xi Zhang, Yu-Ming Shang, Feiran Huang, and Haoran Jia. 2024. Evidence retrieval is almost all you need for fact verification. In Findings of the Association for Computational Linguistics: ACL 2024, pages 9274–9281, Bangkok, Thailand. Association for Computational Linguistic… find
  52. Wanjun Zhong, Jingjing Xu, Duyu Tang, Zenan Xu, Nan Duan, Ming Zhou, Jiahai Wang, and Jian Yin. 2020. Reasoning over semantic-level graph for fact checking. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6170–6180, Online. Association for Computatio…
  53. Jie Zhou, Xu Han, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. 2019. GEAR: Graph-based evidence aggregating and reasoning for fact verification. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 892–901, Florence, Italy. Associ…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tran-2026-semviqa-semantic-question-answering-system/