Relation-Graph Reasoning and Transfer for Cross-Domain Document-Level Event Argument Extraction

Authors

  • Terence Chan School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510275, China
  • Bernard Yip Department of Electronic Engineering and Computer Science, School of Science and Technology, Hong Kong Metropolitan University, Hong Kong, China

DOI:

https://doi.org/10.66421/int.j.datasci.intell.syst45

Keywords:

Event Argument Extraction, Graph Neural Networks, Cross-Domain Transfer, Information Extraction, Natural Language Processing

Abstract

Document-level event argument extraction is a critical and challenging task in information extraction, requiring systems to identify and classify event participants scattered across multiple sentences. While recent advancements in graph neural networks and transformer-based architectures have significantly improved performance within single-domain settings, these models often suffer severe performance degradation when applied to out-of-domain documents. This paper proposes a comprehensive framework that integrates relation-graph reasoning with cross-domain transfer learning to address the challenges of domain shift and long-distance dependencies in document-level event argument extraction. We introduce a heterogeneous document graph structure that models entities, mentions, sentences, and their complex interactions, enabling explicit reasoning over long-range contexts. To facilitate effective domain transfer, we propose a domain-adversarial graph adaptation mechanism that aligns feature distributions across source and target domains at both the node and graph levels. Extensive theoretical and empirical analyses are conducted to evaluate the proposed architecture. The integration of structural reasoning and distributional alignment allows the model to capture domain-invariant structural patterns while maintaining high discriminative power for event argument classification. Experimental evaluations across multiple domain scenarios demonstrate the superiority of the proposed framework over existing baseline models. The findings underscore the importance of structural alignment in cross-domain natural language processing tasks and provide a robust foundation for future research in scalable and adaptable information extraction systems.

References

1. Wei, W. D., Fang, H. B., Liu, Y. D., Shi, J. X., Kwok, J., & Li, Y. F. (2026). Activation Compression in LLMs: Theoretical Analysis and Efficient Algorithm. arXiv preprint arXiv:2605.01255.

2. Luong, M.-T., Pham, H., & Manning, C. D. (2015). Effective approaches to attention-based neural machine translation. In Proceedings of EMNLP.

3. Sang, Y. (2025, October). AutoCrit: A Meta-Reasoning Framework for Self-Critique and Iterative Error Correction in LLM Chains-of-Thought. In 2025 6th International Conference on Machine Learning and Computer Application (ICMLCA) (pp. 1177-1180). IEEE.

4. Xu, X., Tu, W., & Yang, Y. (2023). CASE-Net: Integrating local and non-local attention operations for speech enhancement. Speech Communication, 148, 31-39.

5. Wang, H., Xu, Q., Liu, C., Wu, J., Lin, F., & Chen, W. (2026, April). Emergent hierarchical reasoning in llms through reinforcement learning. In International Conference on Learning Representations (Vol. 2026, pp. 74519-74543).

6. Yang Y, Yang X, Jiang Y, et al. GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems[J]. arXiv preprint arXiv:2602.15776, 2026.

7. Tang, J., Yang, Y., Yu, J., Wang, Z. X., Liang, H., Yao, L., & Yin, J. (2025, November). Unco: Uncertainty-driven collaborative framework of large and small models for grounded multimodal ner. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 7644-7662).

8. Zhu, R., Jiang, X., Wu, J., Ma, Z., Song, J., Bai, F., ... & He, C. (2025, April). GRAIT: gradient-driven refusal-aware instruction tuning for effective hallucination mitigation. In Findings of the Association for Computational Linguistics: NAACL 2025 (pp. 4006-4021).

9. Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., et al. (2020). Language models are few-shot learners. In Advances in Neural Information Processing Systems.

10. Liu, H., Ding, L., & Henao, R. (2026, July). Learning to Control Summaries with Score Ranking. In Findings of the Association for Computational Linguistics: ACL 2026(pp. 35336-35359).

11. Beltagy, I., Peters, M. E., & Cohan, A. (2020). Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150.

12. Zhang, Y., Zhang, Y., Zhao, M., Feng, S., & Cheung, Y. M. (2026). How to Ask the AI: A User Perspective Survey for Large Language Model Prompting.IEEE Transactions on Artificial Intelligence.

13. Li, X., Wang, P., Li, G., Ni, L., & Zhang, Y. (2023). Design of interface circuits and lightweight PUF for TMR sensors. IEEE Sensors Journal, 23(11), 11754-11761.

14. Zhu, R., Ma, Z., Wu, J., Gao, J., Wang, J., Lin, D., & He, C. (2025, April). Utilize the flow before stepping into the same river twice: Certainty represented knowledge flow for refusal-aware instruction tuning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 24, pp. 26157-26165).

15. Yu, H., Zhang, J., Chen, C., Xiang, T., Fang, Y., Niebles, J. C., & Adeli, E. (2026, March). Socialgen: Modeling multi-human social interaction with language models. In 2026 International Conference on 3D Vision (3DV) (pp. 1-17). IEEE.

16. Zhou, J., Shuang, K., An, Z., Guo, J., & Loo, J. (2023). Improving document-level event detection with event relation graph. Information Sciences, 645, 119355.

17. Xu, X., Xie, H., Qin, S. J., Li, L., Tao, X., & Wang, F. L. (2026). Delayed commitment for representation readiness in stage-wise audio-visual learning.arXiv preprint arXiv:2605.01673.

18. Sang, Y. (2025, July). Towards explainable rag: Interpreting the influence of retrieved passages on generation. In 2025 4th International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC) (pp. 397-400). IEEE.

19. Pei, Z., Huang, Q., & Wang, S. (2026). When LLMs develop languages: Symbolic communication for efficient multi-agent reasoning.arXiv preprint arXiv:2606.29354.

20. Li, Y., Bai, X., Liu, S., & Zhang, L. (2026). RepBench: Compiling benchmarks into capability representations for large language models. arXiv. https://arxiv.org/abs/2607.28008

21. Xu, X., Tu, W., & Yang, Y. (2023, June). Selector-enhancer: learning dynamic selection of local and non-local attention operation for speech enhancement. In Proceedings of the AAAI conference on artificial intelligence (Vol. 37, No. 11, pp. 13853-13860).

22. Xie, Z., Liao, R., Wang, Z., Chen, C., Hua, X. S., & Luo, X. (2026, July). GALA: Geometric Data Selection with Strategic Prospecting for Large Language Model Self-training. In Findings of the Association for Computational Linguistics: ACL 2026(pp. 10281-10293).

23. Han, C., Ma, Y., Tan, J., Zheng, W., & Tang, X. (2026, March). Beyond detection: Exploring evidence-based multi-agent debate for misinformation intervention and persuasion. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 45, pp. 38542-38550).

24. Yao, Y., Xiao, W., Miao, P., Chen, G., Yang, H., Chae, C. B., & Wong, K. K. (2026). UAV-RHS-enabled full-duplex ISAC covert system: Robust beamforming and trajectory optimization. IEEE Transactions on Communications.

25. Tang, J., Wang, Z., Gong, Z., Yu, J., Zhu, X., & Yin, J. (2025, April). Multi-grained query-guided set prediction network for grounded multimodal named entity recognition. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 24, pp. 25246-25254).

26. Wang, S., Zhang, X., Wang, P., & Li, X. (2026). Design of Magnetic Sensor Array-Based PUFs for IoT Security. IEEE Transactions on Instrumentation and Measurement, 75, 1-9.

27. Yao, Y., Xiao, W., Miao, P., Chen, G., Yang, H., Chae, C. B., & Wong, K. K. (2025). UAV-relay-aided secure maritime networks coexisting with satellite networks: robust beamforming and trajectory optimization. IEEE Transactions on Wireless Communications.

28. Sang, Y. (2025, August). Robustness of fine-tuned llms under noisy retrieval inputs. In 2025 6th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) (pp. 417-420). IEEE.

29. Xu, X., Wang, Y., Xu, D., Peng, Y., Zhang, C., Jia, J., & Chen, B. (2022, May). Vsegan: Visual speech enhancement gene