Counterfactual Contrastive Decoding for Noisy Multilingual Summarization Streams Under Noisy Multilingual Input Stream Perturbations
Main Article Content
Abstract
The exponential growth of digital communication has necessitated the development of robust multilingual natural language processing systems capable of processing real time input streams. Multilingual summarization, in particular, has emerged as a critical tool for digesting vast quantities of global information. However, input streams in real world applications are rarely pristine. They are often corrupted by various forms of noise, including automated speech recognition errors, machine translation artifacts, optical character recognition inaccuracies, and informal linguistic variations. Traditional sequence to sequence models tend to hallucinate or propagate these errors into the final summary, severely degrading utility and factual accuracy. To address this persistent challenge, this paper introduces a novel decoding strategy termed Counterfactual Contrastive Decoding. By simultaneously evaluating the token generation probabilities of a base model exposed to the noisy input and a counterfactual distribution representing a simulated clean or contrastive state, our method systematically downweights tokens that are disproportionately influenced by input noise. We present a comprehensive theoretical framework and empirical evaluation across numerous languages and noise conditions. Our findings indicate that Counterfactual Contrastive Decoding significantly enhances the robustness, factual consistency, and readability of generated summaries without requiring expensive model retraining or architectural modifications. This research provides a scalable, inference time solution to one of the most pressing challenges in contemporary multilingual text generation.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the Journal of the Artificial Intelligence Engineers Consortium (JAIEC) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, reproduction, and adaptation in any medium, provided the original author(s) and source are properly credited.
Authors retain copyright of their work while granting the journal the right of first publication.
References
1. Zhou, D. (2025, December). M-VP2: Microservice-Oriented Vulnerability Patch Planning-A Cost-Aware Approachusing Multi-Agent Reinforcement Learning. In 2025 5th International Conference on Computer, Internet of Things and Control Engineering (CITCE) (pp. 248-254). IEEE.
2. Zhang, Jiaquan, et al. "Lightweight llm agent memory with small language models." arXiv preprint arXiv:2604.07798 (2026).
3. Zhang, W., & Pei, S. (2026). Predictive prefetching for retrieval-augmented generation. Proceedings of Machine Learning Research. The Forty-third International Conference on Machine Learning, ICML 2026. https://par.nsf.gov/biblio/10686293
4. Chen, Y., Zhao, C., & Gao, Y. (2025). Blockchain applications in health insurance: a review of applications, challenges, and prospects. Frontiers in Blockchain, 8, 1699290.
5. Qu, W., Wang, J., Gong, Y., Huang, X., & Xiao, L. (2025). An end-to-end robust point cloud semantic segmentation network with single-step conditional diffusion models. In Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 27325-27335).
6. Zhou, D. (2026). AI-Driven Hybrid SAST–DAST–SCA–IAST Framework for Risk-Based Vulnerability Prioritization in Microservice Architectures.
7. 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.
8. Yao, S., Guo, J., Li, J., Ou, J., Feng, Y., Hu, J., & Liu, D. (2025). Adversarial hard negative samples for continual relation extraction. Applied Soft Computing, 181, 113365.
9. Chen, C., Zhang, J., Lakshmikanth, S. K., Fang, Y., Shao, R., Wetzstein, G., ... & Adeli, E. (2025). The language of motion: Unifying verbal and non-verbal language of 3d human motion. In Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 6200-6211).
10. Huang, Z., Wang, J., Chen, L., Xiao, B., Cai, L., Zeng, Y., & Xu, J. (2025, October). MVISU-Bench: Benchmarking Mobile Agents for Real-World Tasks by Multi-App, Vague, Interactive, Single-App and Unethical Instructions. In Proceedings of the 33rd ACM International Conference on Multimedia (pp. 8797-8805).
11. Deng, L., Deng, S., Chen, Y., Dai, Y., Zhong, Z., Li, L., ... & Huang, H. (2026). Tool-Augmented Agent for Closed-loop Optimization, Simulation, and Modeling Orchestration. arXiv preprint arXiv:2605.20190.
12. Li, J., Shuang, K., Guo, J., Shi, Z., & Wang, H. (2023). Enhancing semantic relation classification with shortest dependency path reasoning. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31, 1550-1560.
13. Ma, Y., Qu, D., & Pyrozhenko, M. (2026). Bio-RegNet: A Meta-Homeostatic Bayesian Neural Network Framework Integrating Treg-Inspired Immunoregulation and Autophagic Optimization for Adaptive Community Detection and Stable Intelligence. Biomimetics, 11(1), 48.
14. Zhang, W., Zhang, C., Luo, Z., Ma, J., Yuan, W., Gu, C., & Feng, C. (2025). SemanticForge: Repository-Level Code Generation through Semantic Knowledge Graphs and Constraint Satisfaction. arXiv preprint arXiv:2511.07584.
15. Wang, J., Zhao, R., Wei, W., Wang, Y., Yu, M., Zhou, J., ... & Xu, L. (2026, March). Comorag: A cognitive-inspired memory-organized rag for stateful long narrative reasoning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 39, pp. 33557-33565).
16. Qu, D., & Ma, Y. (2025). Magnet-bn: markov-guided Bayesian neural networks for calibrated long-horizon sequence forecasting and community tracking. Mathematics, 13(17), 2740.
17. Liu, T., Jia, Y., Zeng, S., & Yan, J. (2026). Social media use and attitudes toward premarital sex in China: a chain-mediating analysis. Sexuality Research and Social Policy, 1-17.
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. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems.
20. Deng, L., Guo, H., Bai, Y., Dai, Y., Huang, H., & Shi, Y. (2025). BrepLLM: Native Boundary Representation Understanding with Large Language Models. arXiv preprint arXiv:2512.16413.
21. Chen, L. (2026). Beyond external constraints: The missing dimension of ai governance. Available at SSRN 6449738.
22. Xiao, Q., & Zhou, K. (2026). MACD: Model-Aware Contrastive Decoding via Counterfactual Data. arXiv preprint arXiv:2602.01740.
23. Z. Hang, Y. Yashengjiang, J. Li, H. Dong, Y. Wei, Z. Hao, J. Ma, S. Bai, H. Kai, X. Yue, G. Si, D. Jiang, C. Yao, Z. Hu, J. Zhang, P. Liu, Y. Shen, X. Ren, L. Liu, Z. Xu, H. Li, Q. Yao, H. Dong, and H. Wang, “PDEAgent-Bench: A multi-metric, multi-library benchmark for PDE solver generation,” arXiv preprint arXiv:2605.09636, 2026, doi: 10.48550/arXiv.2605.09636.
24. Yang, Y., Yang, X., Jiang, Y., Mu, N., Hu, H., Xie, R., ... & Xu, B. (2026). GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems. arXiv preprint arXiv:2602.15776.
25. Wang, Juyuan, et al. "HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads." arXiv preprint arXiv:2604.17237 (2026).
26. Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proceedings of EMNLP.
27. Wang, Chenxing, et al. "When & How to Write for Personalized Demand-aware Query Rewriting in Video Search." arXiv preprint arXiv:2602.17667 (2025).
28. Xu, Z., Wu, Y., & Zhao, Y. (2026). TRIZ-RAGNER: A Retrieval-Augmented Large Language Model for TRIZ-Aware Named Entity Recognition in Patent-Based Contradiction Mining. arXiv preprint arXiv:2602.23656.
29. Xu, X., Tu, W., & Yang, Y. (2023). CASE-Net: Integrating local and non-local attention operations for speech enhancement. Speech Communication, 148, 31-39.
30. 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.
31. Guo, J., Shuang, K., Li, J., Wang, Z., & Liu, Y. (2022, May). Beyond the granularity: Multi-perspective dialogue collaborative selection for dialogue state tracking. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 2320-2332).
32. Peters, M. E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018). Deep contextualized word representations. In Proceedings of NAACL-HLT.
33. Guo, J., Yang, L., Chen, P., Xiao, Q., Wang, Y., Juan, X., ... & Wang, M. (2025). GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators. arXiv preprint arXiv:2512.19682.
34. Ou, J., Guo, J., Jiang, S., Wang, Z., Chen, Y., Xue, R., & Tian, W. (2025, June). Low-Rank Decomposition Assisted Quantization and Inference Compensation for Quality Large Language Model Inference. In 2025 International Joint Conference on Neural Networks (IJCNN) (pp. 1-9). IEEE.
35. Lv, Z., Wang, Q., Lyu, T., & Dong, J. (2026). A Deep Learning-Based Model for User Emotion Recognition and Behavior Guidance Design: EMoGuideNet-An Emotion-Aware Multimodal Framework for Enhancing Intelligent User Interaction. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-30.
36. Zhou, J., Shuang, K., An, Z., Guo, J., & Loo, J. (2023). Improving document-level event detection with event relation graph. Information Sciences, 645, 119355.
37. Zhang, H., Chen, J., Wu, D., Li, Y., Zhang, Y., Zhang, X. T., ... & Tian, F. (2026). Duplexsla: A full-duplex spoken language model with synchronized speech, language, and action. arXiv preprint arXiv:2605.20755.
38. Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2002). BLEU: A method for automatic evaluation of machine translation. In Proceedings of ACL.
39. Xu, X., Wang, Y., Xu, D., Peng, Y., Zhang, C., Jia, J., & Chen, B. (2022, May). Vsegan: Visual speech enhancement generative adversarial network. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7308-7311). IEEE.
40. 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.
41. Zhang, Jiaquan, et al. "Learning global hypothesis space for enhancing synergistic reasoning chain." arXiv preprint arXiv:2602.09794 (2026).
42. 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.
43. Zhu, Runchuan, et al. "AdaptFlow: Adaptive Workflow Optimization via Meta-Learning." arXiv preprint arXiv:2508.08053 (2025).
44. Ding, H., Fang, Y., Zhu, R., Jiang, X., Zhang, J., Xu, Y., ... & Wang, Y. (2024). 3ds: Decomposed difficulty data selection’s case study on llm medical domain adaptation.