Elamur Research⌕
☰
home / papers / 2026 / BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection

BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection

Paper · 2026 · Zhongxing Zhang, Emily K. Vraga, Jisu Huh et al.

Summary

The paper addresses automatic detection of incorrect information, such as misinformation and rumors on social media. Existing detectors typically merge text features and external knowledge into a single classifier, so the contribution of each source cannot be separated. They also suffer from attention collapse. BiMind addresses this with two parallel prediction heads. One reasons only over the input text. The other draws on knowledge retrieved from an in-domain memory built from the training set itself. The text encoder uses an attention geometry adapter, which adjusts pre-softmax attention scores with token-dependent offsets. Retrieved nearest neighbours are injected through FiLM. The two heads are combined by entropy-gated fusion or a learned agreement head, with a symmetric KL term encouraging consistency between them. A new metric, Value-of-eXperience (VoX), measures per-instance logit gains from the knowledge head. On four public datasets, BiMind generally beats CNN, GCN, BERT, HAN and HeteroSGT baselines. Its explicit separation of the two reasoning streams shows when external knowledge actually helps.

Key points

  • Evaluated on MM COVID, ReCOVery, MC Fake and LIAR. BiMind's accuracy is 0.951, 0.918, 0.887 and 0.633 respectively, the best in each case. On MC Fake its F1 (0.738) trails HeteroSGT (0.783).
  • VoX is clearly positive on MM COVID (mean +0.97, about 83% of samples gain) and ReCOVery (+0.47, about 84%). It is slightly negative on MC Fake (−0.08, about 40% gain), indicating that knowledge does not always help.
  • In the ReCOVery ablation, the full model reaches 0.897 accuracy and 0.895 F1. Removing knowledge retrieval causes the largest drop, to 0.847 accuracy. Removing AGA lowers accuracy to 0.872.
  • Code and datasets are released at github.com/cvzh/BiMind.
  • The authors list several limitations: no use of social-credibility or propagation signals, text-only scope, and weaker AGA benefit for inputs with few salient lexical cues.

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

🎓University of MinnesotaMinneapolis · United States28 works · 2,184 citations

 Fields, topics and concepts

📚 Shelves 7The 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 worksComputer Vision and Pattern Recognition · 2,869 worksSocial Sciences · 1,772 worksSociology and Political Science · 577 works

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1,426 works

Cite

Cite as Zhongxing Zhang, Emily K. Vraga, Jisu Huh and Jaideep Srivastava. 2026. BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.713

@inproceedings{zhang2026bimind,
  title = {{BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection}},
  author = {Zhongxing Zhang, Emily K. Vraga, Jisu Huh and Jaideep Srivastava},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.713},
  url = {https://doi.org/10.18653/v1/2026.acl-long.713}
}

References

72 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sara Abdali, Sina Shaham, and Bhaskar Krishnamachari. 2024. Multi-modal misinformation detection: Approaches, challenges and opportunities. ACM Computing Surveys, 57(3):1–29. find
  2. Sajjad Ahmed, Knut Hinkelmann, and Flavio Corradini. 2022. Combining machine learning with knowledge engineering to detect fake news in social networks-a survey. arXiv preprint arXiv:2201.08032. — [arXiv:2201.08032](https://arxiv.org/abs/2201.08032) find
  3. Bimal Bhattarai, Ole-Christoffer Granmo, and Lei Jiao. 2021. Explainable tsetlin machine framework for fake news detection with credibility score assessment. arXiv preprint arXiv:2105.09114. find
  4. Tian Bian, Xi Xiao, Tingyang Xu, Peilin Zhao, Wenbing Huang, Yu Rong, and Junzhou Huang. 2020. Rumor detection on social media with bi-directional graph convolutional networks. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 549–556. find
  5. Xi Chen, Wei Xue, and Yike Guo. 2026. Actormind: Emulating human actor reasoning for speech role-playing. arXiv preprint arXiv:2604.11103. pages 2114–2119, Online. Association for Computational Linguistics. find
  6. Boyi Deng, Wenjie Wang, Fengbin Zhu, Qifan Wang, and Fuli Feng. 2025. Cram: Credibility-aware attention modification in llms for combating misinformation in rag. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 23760–23768. find
  7. 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,…
  8. Yingtong Dou, Kai Shu, Congying Xia, Philip S. Yu, and Lichao Sun. 2021. User preference-aware fake news detection. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2051– 2055. find
  9. Yaqian Dun, Kefei Tu, Chen Chen, Chunyan Hou, and Xiaojie Yuan. 2021. Kan: Knowledge-aware attention network for fake news detection. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 81–89. find
  10. Oren Etzioni, Michele Banko, Stephen Soderland, and Daniel S Weld. 2008. Open information extraction from the web. Communications of the ACM, 51(12):68–74.
  11. Dongqi Fu, Yikun Ban, Hanghang Tong, Ross Maciejewski, and Jingrui He. 2022. Disco: Comprehensive and explainable disinformation detection. Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pages 4848–4852. find
  12. Amira Ghenai and Yelena Mejova. 2018. Fake cures: user-centric modeling of health misinformation in social media. In Proceedings of the ACM on Human-Computer Interaction, pages 1–20. find
  13. Bin Guo, Yasan Ding, Lina Yao, Yunji Liang, and Zhiwen Yu. 2020. The future of false information detection on social media: New perspectives and trends. ACM Computing Survery, 53(4):1–36. find
  14. Alexis Conneau and Guillaume Lample. 2019. Cross-lingual language model pretraining. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, pages 7059–7069. find
  15. Zhijiang Guo, Michael Schlichtkrull, and Andreas Vlachos. 2022. A survey on automated fact-checking. Transactions of the Association for Computational Linguistics, 10:178–206.
  16. Danilo Croce, Giuseppe Castellucci, and Roberto Basili. 2020. GAN-BERT: Generative adversarial learning for robust text classification with a bunch of labeled examples. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Kelvin Guu, Kenton Lee, Zora Tung, Panu… find
  17. Syed Mustafa Haider Rizvi, Ramsha Imran, and Arif Mahmood. 2025. Text classification using graph convolutional networks: A comprehensive survey. ACM Computing Survery, 57(8). find
  18. Naeemul Hassan, Chengkai Li, and Mark Tremayne. 2015. Detecting check-worthy factual claims in presidential debates. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pages 1835–1838. find
  19. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2020. Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654.
  20. Ammar Ismael Kadhim. 2019. Survey on supervised machine learning techniques for automatic text classification. Artificial Intelligence Review, 52:273–292. find
  21. Rohit Kumar Kaliyar, Anurag Goswami, and Pratik Narang. 2021. Fakebert: Fake news detection in social media with a bert-based deep learning approach. Multimedia Tools and Applications, 80(8):11765– 11788. find
  22. Rohit Kumar Kaliyar, Anurag Goswami, Pratik Narang, and Soumendu Sinha. 2020. Fndnet–a deep convolutional neural network for fake news detection. Cognitive Systems Research, 61:32–44. find
  23. Yoon Kim. 2014. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 1746–1751, Doha, Qatar. Association for Computational Linguistics.
  24. Guangchen Lan, Huseyin A Inan, Sahar Abdelnabi, Janardhan Kulkarni, Lukas Wutschitz, Reza Shokri, Christopher G Brinton, and Robert Sim. 2025. Contextual integrity in llms via reasoning and reinforcement learning. arXiv preprint arXiv:2506.04245. find
  25. 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…
  26. Guoyi Li, Die Hu, Zongzhen Liu, Xiaodan Zhang, and Honglei Lyu. 2025. Semantic reshuffling with LLM and heterogeneous graph auto-encoder for enhanced rumor detection. In Proceedings of the 31st International Conference on Computational Linguistics, pages 8557–8572, Abu Dhabi, UAE. Association for Co… find
  27. Yichuan Li, Bohan Jiang, Kai Shu, and Huan Liu. 2020. Mm-covid: A multilingual and multimodal data repository for combating covid-19 disinformation. arXiv preprint arXiv:2011.04088. — [arXiv:2011.04088](https://arxiv.org/abs/2011.04088) find
  28. Hu Linmei, Tianchi Yang, Chuan Shi, Houye Ji, and Xiaoli Li. 2019. Heterogeneous graph attention networks for semi-supervised short text classification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Lan… find
  29. 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. arXiv preprint arXiv:1907.11692.
  30. TaiMing Lu and Philipp Koehn. 2025. Learn and unlearn: Addressing misinformation in multilingual LLMs. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 10191–10206, Suzhou, China. Association for Computational Linguistics. find
  31. Jing Ma, Wei Gao, Prasenjit Mitra, Sejeong Kwon, Bernard J. Jansen, Kam-Fai Wong, and Meeyoung Cha. 2016. Detecting rumors from microblogs with recurrent neural networks. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, pages 3818–3824. find
  32. Jing Ma, Wei Gao, and Kam-Fai Wong. 2018. Rumor detection on Twitter with tree-structured recursive neural networks. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1980–1989, Melbourne, Australia. Association for Computationa…
  33. Qianli Ma, Zhenxi Lin, Jiangyue Yan, Zipeng Chen, and Liuhong Yu. 2020. MODE-LSTM: A parameter-efficient recurrent network with multi-scale for sentence classification. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 6705–6715, Online. Association for… find
  34. Valeria Mazzeo, Andrea Rapisarda, and Giovanni Giuffrida. 2021. Detection of fake news on covid-19 on web search engines. Frontiers in Physics, 9:685730. find
  35. Erxue Min, Yu Rong, Yatao Bian, Tingyang Xu, Peilin Zhao, Junzhou Huang, and Sophia Ananiadou. 2022. Divide-and-conquer: Post-user interaction network for fake news detection on social media. In Proceedings of the ACM Web Conference, pages 1148–1158. find
  36. Shervin Minaee, Nal Kalchbrenner, Erik Cambria, Narjes Nikzad, Meysam Chenaghlu, and Jianfeng Gao. 2021. Deep learning–based text classification: A comprehensive review. ACM Computing Survery, 54(3). find
  37. Ethan Perez, Florian Strub, Harm De Vries, Vincent Dumoulin, and Aaron Courville. 2018. Film: Visual reasoning with a general conditioning layer. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 3942–3951.
  38. Kashyap Popat. 2017. Assessing the credibility of claims on the web. In Proceedings of the 26th International Conference on World Wide Web Companion, pages 735–739. find
  39. Nils Reimers and Iryna Gurevych. 2019. 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, pages 3982–3992, Hong Kong, Chin…
  40. Natali Ruchansky, Sungyong Seo, and Yan Liu. 2017. Csi: A hybrid deep model for fake news detection. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pages 797– 806. find
  41. Devendra Singh Sachan, Manzil Zaheer, and Ruslan Salakhutdinov. 2019. Revisiting lstm networks for semi-supervised text classification via mixed objective function. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 6940–6948. find
  42. Lanyu Shang, Yang Zhang, Bozhang Chen, Ruohan Zong, Zhenrui Yue, Huimin Zeng, Na Wei, and Dong Wang. 2024. Mmadapt: A knowledge-guided multi-source multi-class domain adaptive framework for early health misinformation detection. In Proceedings of the ACM Web Conference, pages 4653–4663. find
  43. Xian Teng, Yu-Ru Lin, Wen-Ting Chung, Ang Li, and Adriana Kovashka. 2022. Characterizing user susceptibility to covid-19 misinformation on twitter. In Proceedings of the International AAAI Conference on Web and Social Media, pages 1005–1016. find
  44. Kjerstin Thorson, Emily Vraga, and Brian Ekdale. 2010. Credibility in context: How uncivil online commentary affects news credibility. Mass Communication and Society, 13(3):289–313. find
  45. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, and 1 others. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  46. Shu-Feng Tsao, Helen Chen, Therese Tisseverasinghe, Yang Yang, Lianghua Li, and Zahid A Butt. 2021. What social media told us in the time of covid-19: a scoping review. The Lancet Digital Health, 3(3):e175–e194. find
  47. Jens Van Nooten and Walter Daelemans. 2025. Jump to hyperspace: Comparing Euclidean and hyperbolic loss functions for hierarchical multi-label text classification. In Proceedings of the 31st International Conference on Computational Linguistics, pages 4260– 4273, Abu Dhabi, UAE. Association for Comp… find
  48. Baoxu Shi and Tim Weninger. 2016. Fact checking in heterogeneous information networks. In Proceedings of the 25th International Conference Companion on World Wide Web, pages 101–102. find
  49. Andreas Vlachos and Sebastian Riedel. 2014. Fact checking: Task definition and dataset construction. In Proceedings of the ACL 2014 Workshop on Language Technologies and Computational Social Science, pages 18–22.
  50. Chongyang Shi, Yijun Yin, Qi Zhang, Liang Xiao, Usman Naseem, Shoujin Wang, and Liang Hu. 2023. Multiview clickbait detection via jointly modeling subjective and objective preference. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 11807–11816, Singapore. Association… find
  51. Nguyen Vo and Kyumin Lee. 2018. The rise of guardians: Fact-checking url recommendation to combat fake news. In Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pages 275– 284. find
  52. Kai Shu, Amy Sliva, Suhang Wang, Jiliang Tang, and Huan Liu. 2017. Fake news detection on social media: a data mining perspective. SIGKDD Explor. Newsl., 19(1):22–36. find
  53. Kai Shu, Suhang Wang, and Huan Liu. 2019. Beyond news contents: The role of social context for fake news detection. In Proceedings of the 12nd ACM International Conference on Web Search and Data Mining, pages 312–320. find
  54. Qi Su, Mingyu Wan, Xiaoqian Liu, and Chu-Ren Huang. 2020. Motivations, methods and metrics of misinformation detection: an nlp perspective. Natural Language Processing Research, 1(1):1–13. find
  55. Xiaobing Sun and Wei Lu. 2020. Understanding attention for text classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3418–3428, Online. Association for Computational Linguistics. find
  56. William Yang Wang. 2017. “liar, liar pants on fire”: A new benchmark dataset for fake news detection. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 422–426, Vancouver, Canada. Association for Computational Linguistics.
  57. Xuepeng Wang, Kang Liu, Shizhu He, and Jun Zhao. 2016. Learning to represent review with tensor decomposition for spam detection. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 866–875, Austin, Texas. Association for Computational Linguistics. find
  58. Yaqing Wang, Fenglong Ma, Zhiwei Jin, Ye Yuan, Guangxu Xun, Kishlay Jha, Lu Su, and Jing Gao. 2018. Eann: Event adversarial neural networks for multi-modal fake news detection. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 849– 857. find
  59. Jiaying Wu, Jiafeng Guo, and Bryan Hooi. 2024. Fake news in sheep’s clothing: Robust fake news detection against llm-empowered style attacks. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 3367–3378. find
  60. You Wu, Pankaj K. Agarwal, Chengkai Li, Jun Yang, and Cong Yu. 2014. Toward computational fact-checking. In Proceedings of the VLDB Endowment, pages 589–600. find
  61. Yijin Xiong, Yukun Feng, Hao Wu, Hidetaka Kamigaito, and Manabu Okumura. 2021. Fusing label embedding into BERT: An efficient improvement for text classification. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1743–1750, Online. Association for Computational Lin… find
  62. Information & Knowledge Management, pages 3205– 3212. find
  63. Xinyi Zhou and Reza Zafarani. 2019. Network-based fake news detection: A pattern-driven approach. arXiv preprint arXiv:1906.04210. — [arXiv:1906.04210](https://arxiv.org/abs/1906.04210) find
  64. Xinyi Zhou and Reza Zafarani. 2020. A survey of fake news: Fundamental theories, detection methods, and opportunities. ACM Computing Survery, 53(5). find
  65. Junyou Zhu, Chao Gao, Ze Yin, Xianghua Li, and Juergen Kurths. 2024. Propagation structure-aware graph transformer for robust and interpretable fake news detection. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 4652–4663. find
  66. Chang Yang, Peng Zhang, Wenbo Qiao, Hui Gao, and Jiaming Zhao. 2023. Rumor detection on social media with crowd intelligence and ChatGPT-assisted networks. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5705–5717, Singapore. Association for Computati… find
  67. Zichao Yang, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola, and Eduard Hovy. 2016. Hierarchical attention networks for document classification. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 14…
  68. Liang Yao, Chengsheng Mao, and Yuan Luo. 2018. Graph convolutional networks for text classification. arXiv preprint arXiv:1809.05679. find
  69. Jungmin Yun, Mihyeon Kim, and Youngbin Kim. 2023. Focus on the core: Efficient attention via pruned token compression for document classification. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13617–13628, Singapore. Association for Computational Linguistics. find
  70. Amy X. Zhang, Aditya Ranganathan, Sarah Emlen Metz, Scott Appling, Connie Moon Sehat, Norman Gilmore, Nick B. Adams, Emmanuel Vincent, Jennifer Lee, Martin Robbins, Ed Bice, Sandro Hawke, David Karger, and An Xiao Mina. 2018. A structured response to misinformation: Defining and annotating credibili… find
  71. Yuchen Zhang, Xiaoxiao Ma, Jia Wu, Jian Yang, and Hao Fan. 2024. Heterogeneous subgraph transformer for fake news detection. In Proceedings of the ACM Web Conference, pages 1272–1282. find
  72. Xinyi Zhou, Apurva Mulay, Emilio Ferrara, and Reza Zafarani. 2020. Recovery: A multimodal repository for covid-19 news credibility research. In Proceedings of the 29th ACM International Conference on find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-bimind-dual-head-reasoning-model/