Weixuan Wang

I’m a Research Scientist at the Ant International working on multilingual LLMs and Fintech.

I am particularly interested in developing general AI techniques that enable LLMs to better understand and serve users across languages and domains, with applications in FinTech and global AI systems.

Please reach out to collaborate 😃

• Weixuan Wang, Minghao Wu, Barry Haddow, and Alexandra Birch (2025). Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization. ICLR2026.
• Weixuan Wang, Dongge Han, Daniel Madrigal Diaz, Jin Xu, Victor Rühle, and Saravan Rajmohan (2025). OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows. arXiv:2508.09124.
• Weixuan Wang, Minghao Wu, Barry Haddow, and Alexandra Birch (2025). HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language Models. ICLR2026.
• Weixuan Wang, Minghao Wu, Barry Haddow, and Alexandra Birch (2025). ExpertSteer: Intervening in LLMs through Expert Knowledge. 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:2504.15521.
• Weixuan Wang, Minghao Wu, Barry Haddow, and Alexandra Birch (2025). Demystifying multilingual chain-of-thought in process reward modeling. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. (EMNLP25, Findings)
• Sherrie Shen, Weixuan Wang, and Alexandra Birch (2025). Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine Translation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.(EMNLP25, Main)
• 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:2501.11036.
• Weixuan Wang, Minghao Wu, Barry Haddow, and Alexandra Birch (2025). Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5418–5433. (ACL25, Oral, OutStanding Paper Award)
• Weixuan Wang, Jingyuan Yang, and Wei Peng. (2025). Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors. In The Thirteenth International Conference on Learning Representations. (ICLR25)
• Weixuan Wang, Barry Haddow, Minghao Wu, Wei Peng, and Alexandra Birch (2024). Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs. arXiv:2406.09265.
• Weixuan Wang, Barry Haddow, and 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. (ACL24, Main)
• Weixuan Wang, Barry Haddow, Alexandra Birch, and 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. (NAACL24, Main, Oral)
• 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, and 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, and Zhang, Z. (2023). Evaluating the Efficacy of Length-Controllable Machine Translation. arXiv:2305.02300.
• Weixuan Wang, Wei Peng, and Qun Liu (2023). Learning Homographic Disambiguation Representation for Neural Machine Translation. arXiv:2304.05860.
• Weixuan Wang, Choon Meng Lee, Jianfeng Liu, Talha Colakoglu, and 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, and Wei Peng (2022). Huawei BabelTar NMT at WMT22 Biomedical Translation Task: How we further improve domain-specific NMT. In Proceedings of the Seventh Conference on Machine Translation, pages 930-935. (WMT22)
• Feng, Z., Hailong Cao, Tiejun Zhao, Weixuan Wang, and Wei Peng (2022). Cross-lingual feature extraction from monolingual corpora for low-resource unsupervised bilingual lexicon induction. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5278-5287. (COLING22)
• Weixuan Wang, Wei Peng, Chong Hsuan Huang, and Haoran Wang. (2022). Positively transitioned sentiment dialogue corpus for developing emotion-affective open-domain chatbots. arXiv:2208.04565.
• Weixuan Wang, Wei Peng, Meng Zhang, and Qun Liu (2021). Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing pages 3197-3202). (EMNLP21, Main)
• Weixuan Wang, Wei Peng, Xupeng Meng, and Qun Liu (2021). 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, pages 868-873. (WMT21)