Yifan Wang

PhD student, Language Science and Technology, Universität des Saarlandes

Joined

April 2024

Names

Yifan Wang (Preferred)

Emails

****@lst.uni-saarland.de (Confirmed)

Personal Links

Career & Education History

PhD student

Language Science and Technology, Universität des Saarlandes (uni-saarland.de)

2023 – 2027

Advisors, Relations & Conflicts

PhD Advisor

Vera Demberg

2023 – Present

PhD Advisor

Isabel Valera

2023 – Present

Expertise

Fairness

Present

Interpretability

Present

Personalization

Present

Publications

Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?
Yifan Wang, Mayank Jobanputra, Ji-Ung Lee, Soyoung Oh, Isabel Valera, Vera Demberg
- ICLR 2026 Poster
- Readers: Everyone
B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability
Yifan Wang, Sukrut Rao, Ji-Ung Lee, Mayank Jobanputra, Vera Demberg
- Accepted by TMLR
- Readers: Everyone
B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability
Yifan Wang, Sukrut Rao, Ji-Ung Lee, Mayank Jobanputra, Vera Demberg
- CoRR 2025
- Readers: Everyone
SciNews: From Scholarly Complexities to Public Narratives - a Dataset for Scientific News Report Generation
Dongqi Liu, Yifan Wang, Jia E. Loy, Vera Demberg
- LREC/COLING 2024
- Readers: Everyone
RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework
Yifan Wang, Vera Demberg
- EMNLP 2024
- Readers: Everyone
Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization
Dongqi Liu, Yifan Wang, Vera Demberg
- ACL (1) 2023
- Readers: Everyone
Unsupervised Mandarin-Cantonese Machine Translation
Megan Dare, Valentina Fajardo Diaz, Averie Ho Zoen So, Yifan Wang, Shibingfeng Zhang
- CoRR 2023
- Readers: Everyone

Yifan Wang

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?

B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability

B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability

SciNews: From Scholarly Complexities to Public Narratives - a Dataset for Scientific News Report Generation

RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework

Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization

Unsupervised Mandarin-Cantonese Machine Translation

Co-Authors