Yifan Wang
About Me
Hi! I'm Yifan Wang, a third year PhD student as a member of RTG: Neuroexplicit models of language, vision and action project at Saarland University. Currently I'm co-supervised by Prof. Dr. Vera Demberg and Prof. Dr. Isabel Valera. Prior to this, I obtained my Master degree in Language Science and Technology at Saarland University and Bachelor degree in Germanistics at Shanghai Jiaotong University. I have also spent an exchange semester at Heidelberg Univeristy in 2018/19.
My current research focuses on identifying and addressing undesired behaviors in NLP systems, with a particular interest in detecting and mitigating social biases in LLMs. I'm also passionate about improving the interpretability of deep neural networks. Additionally, I'm exploring new research directions that are both interesting and meaningful for the future of AI development.
In my free time, I enjoy walking around in the city. As probably the worst cook in Germany, I'm always willing to join a food adventure (check out some failed fried eggs here).
For further information, welcome to have a look at my CV.
Publications
- Yifan Wang, Mayank Jobanputra, Ji-Ung Lee, Soyoung Oh, Isabel Valera, Vera Demberg. Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection? Preprint, 2025. [paper]
- Yifan Wang, Sukrut Rao, Ji-Ung Lee, Mayank Jobanputra, Vera Demberg. B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability. Transactions on Machine Learning Research (TMLR 2025). [paper]
- Mayank Jobanputra, Alisa Kovtunova, Brisca Balthes, Fedor Grigoryevich Pogulskiy, Yifan Wang, Stefan Borgwardt, Vera Demberg. ProofTeller: Exposing recency bias in LLM reasoning and its side effects on communication. Proceedings of the International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL 2025).
- Mayank Jobanputra, Nils Philipp Walter, Maitrey Mehta, Blerta Veseli, Evan Parker Kelly Chapple, Sneha Chetani, Yifan Wang, Ellie Pavlick, Antonio Vergari, Vera Demberg. Can LLMs subtract numbers? Proceedings of the 3rd Workshop on Mathematical Natural Language Processing (MathNLP 2025). [paper]
- Yifan Wang, Vera Demberg. RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024). [paper]
- Yifan Wang, Vera Demberg. A Parameter-Efficient Multi-Objective Approach to Mitigate Stereotypical Bias in Language Models. Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP 2024). [paper]
- Dongqi Liu, Yifan Wang, Jia Loy, Vera Demberg. SciNews: From Scholarly Complexities to Public Narratives--A Dataset for Scientific News Report Generation. Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). [paper]
- Dongqi Liu, Yifan Wang, Vera Demberg. Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023). [paper]
Academic Services
- Conference Reviewer: ACL ARR 2025
- Jornal Reviewer: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
News
- 11/2025: One paper accepted to TMLR.
- 11/2025: One paper accepted to IJCNLP-AACL 2025.
- 09/2025: One paper accepted to Workshop on Mathematical Natural Language Processing (MathNLP) at EMNLP 2025. Hope to see you in Suzhou, China.
- 07/2025: I will attend ACL 2025 in Vienna, Austria.
- 04/2025: Invited talk on RSA-Control in the McGill NLP reading group at Mila.
- 09/2024: One paper accepted to EMNLP 2025.
- 08/2024: Attended Workshop on Gender Bias in Natural Language Processing (GeBNLP).
Contact
- Email: