Selected Publications

Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention [paper] [code] [website] Weixuan Wang, Minghao Wu, Barry Haddow, Alexandra Birch In Proceedings of 63rd Annual Meeting of the Association for Computational Linguistics, (ACL), 2025

Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors [paper] [code] [website] Weixuan Wang, Jingyuan Yang, Wei Peng In The Thirteenth International Conference on Learning Representations, (ICLR), 2025

Retrieval-Augmented Multilingual Knowledge Editing [paper] [code] [website] [dataset] Weixuan Wang, Barry Haddow, Alexandra Birch In Proceedings of 62nd Annual Meeting of the Association for Computational Linguistics, (ACL), 2024

Assessing the reliability of large language model knowledge [paper] [code] [website] [dataset] [slides] Weixuan Wang, Barry Haddow, Alexandra Birch, Wei Peng In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (NAACL, oral)

---

Publications

• Weixuan Wang, Minghao Wu, Barry Haddow, and Alexandra Birch (2025). HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language Models. arXiv preprint arXiv:2505.12300.
• Weixuan Wang, Minghao Wu, Barry Haddow, and Alexandra Birch (2025). ExpertSteer: Intervening in LLMs through Expert Knowledge. arXiv preprint arXiv:2505.12313.
• Minghao Wu, Weixuan Wang, Sinuo Liu, Huifeng Yin, Xintong Wang, Yu Zhao, Chenyang Lyu, Longyue Wang, Weihua Luo, and Kaifu Zhang (2025). The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks. arXiv preprint arXiv:2504.15521.
• Weixuan Wang, Minghao Wu, Barry Haddow, and Alexandra Birch (2025). Demystifying multilingual chain-of-thought in process reward modeling. arXiv preprint arXiv:2502.12663.
• Yang, Jingyuan, Rongjun Li, Weixuan Wang, Ziyu Zhou, Zhiyong Feng, and Wei Peng (2025). LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models. arXiv preprint arXiv:2501.11036.
• Weixuan Wang, Minghao Wu, Barry Haddow, & Alexandra Birch (2025). Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention. ACL 2025.
• Weixuan Wang, Jingyuan Yang, & Wei Peng. (2025). Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors. In The Thirteenth International Conference on Learning Representations, (ICLR).
• Weixuan Wang, Barry Haddow, Minghao Wu, Wei Peng, & Alexandra Birch (2024). Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs. arXiv preprint arXiv:2406.09265.
• Weixuan Wang, Barry Haddow, & Alexandra Birch (2024). Retrieval-Augmented Multilingual Knowledge Editing. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 335–354.
• Weixuan Wang, Barry Haddow, Alexandra Birch, & Wei Peng (2024). Assessing the reliability of large language model knowledge. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 805–819.
• Hailong Cao, Hualin Miao, Weixuan Wang, Liangyou Li, Wei Peng, and Tiejun Zhao. (2024). Bilingual phrase induction with local hard negative sampling. CAAI Transactions on Intelligence Technology 10, no. 1 (2025): 147-159.
• Hailong Cao, Tiejun Zhao, Weixuan Wang, & Wei Peng (2023). Bilingual word embedding fusion for robust unsupervised bilingual lexicon induction. Information Fusion, 97, 101818.
• Hao Cheng, Meng Zhang, Weixuan Wang, Liangyou Li, Qun Liu, & Zhang, Z. (2023). Evaluating the Efficacy of Length-Controllable Machine Translation. arXiv preprint arXiv:2305.02300.
• Weixuan Wang, Wei Peng, & Qun Liu (2023). Learning Homographic Disambiguation Representation for Neural Machine Translation. arXiv preprint arXiv:2304.05860.
• Weixuan Wang, Choon Meng Lee, Jianfeng Liu, Talha Colakoglu, & Wei Peng (2023). An empirical study of cyclical learning rate on neural machine translation. Natural Language Engineering, 29(2), 316-336.
• Weixuan Wang, Xupeng Meng, Suqing Yan, Ye Tian, & Wei Peng (2022, December). Huawei BabelTar NMT at WMT22 Biomedical Translation Task: How we further improve domain-specific NMT. In Proceedings of the Seventh Conference on Machine Translation (WMT) (pp. 930-935).
• Feng, Z., Hailong Cao, Tiejun Zhao, Weixuan Wang, & Wei Peng (2022, October). Cross-lingual feature extraction from monolingual corpora for low-resource unsupervised bilingual lexicon induction. In Proceedings of the 29th International Conference on Computational Linguistics (pp. 5278-5287).
• Weixuan Wang, Wei Peng, Chong Hsuan Huang, & Wang, H. (2022). Positively transitioned sentiment dialogue corpus for developing emotion-affective open-domain chatbots. arXiv preprint arXiv:2208.04565.
• Weixuan Wang, Wei Peng, Meng Zhang, & Qun Liu (2021, November). Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (pp. 3197-3202).
• Weixuan Wang, Wei Peng, Xupeng Meng, & Qun Liu (2021, November). Huawei aarc’s submissions to the wmt21 biomedical translation task: Domain adaption from a practical perspective. In Proceedings of the Sixth Conference on Machine Translation (pp. 868-873).
• Weixuan Wang, Xiaoling Cai, Huang, Chong Hsuan Huang, Haoran Wang, Haonan Lu, Ximing Liu, & Wei Peng (2021). Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona. arXiv preprint arXiv:2109.08875.
• Xinyue Liu, Weixuan Wang, Wenxin Liang., & Yuangang Li (2020). Speed up the training of neural machine translation. Neural Processing Letters, 51(1), 231-249.
• Xinyue Liu, & Weixuan Wang (2019, December). Multiway Attention for Neural Machine Translation. In Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence (pp. 265-270).