Dr. Yuxia Wang

Research areas: Natural Language Processing

Email: [email protected]

Links: Google Scholar / Homepage

I am a tenure-track faculty member at INSAIT, in Sofia, Bulgaria, where I lead a group working on natural language processing (NLP). My research interests include large language model reasoning, safety, factuality and empathy improvement (multi-objective optimization), real-world application of LLMs in financial and medical domains, and human-AI collaborative interactions. 

Before joining INSAIT, I was a postdoctoral researcher at MBZUAI NLP department, working with Prof. Preslav Nakov. Prior to this, I completed my PhD at The University of Melbourne in January 2023, under the guidance of Prof. Tim Baldwin and Prof. Karin Verspoor.

I am looking for motivated PhD students. If you’re passionate about these topics, feel free to contact me with your CV and a brief introduction of your research interests.

2026

Junjie Liao, Yuxia Wang
Retrieve Few, Verify Many: Segment-Level Evidence Reuse for Long-Form Factuality Assessment
In: The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026) (Findings)

Rania Elbadry, Ahmed Heakl, Saeed Almheiri, Fan Zhang, Muhra AlMahri, Xueqing Peng, Mohsinul Kabir, Shuyao Wang, Yi Han, Saadeldine Eletter, Duzhen Zhang, Preslav Nakov, Yuxia Wang, Fajri Koto, Zhuohan Xie
Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close
In: The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026) (Findings)

Paper

Youssef Mohamed, Ahmed Heakl, Qinrong Cui, Junhong Liang, Rafiq Ali, Bdour Babillie, Nazira Dunbayeva, Lang Gao, Omar Hussein, Ahmed Nada, Ahmed Mohamed Magdy Mohamed, Jinghui Liu, Salman Khan, Xiuying Chen, Yuxia Wang, Imran Razzak
MedRoundsQA: A Persona and Difficulty Aware Evaluation for Multi-Turn Medical Consultations
In: The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)

Paper

Hasan Iqbal, Sarfraz Ahmad, Hyunjae Kim, Sihyeon Park, Junjie Liao, Qingyu Chen, Preslav Nakov, Yuxia Wang
MedSNIP: Building and Benchmarking Snippet-Level Granularity for Medical Fact Verification
In: The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)

Ahmed Sharshar, Hosam Elgendy, Yasser Rohaim, Saadeldine Eletter, Yuxia Wang
Harm or Humor: A Multimodal, Multilingual Benchmark for Overt and Covert Harmful Humor
In: The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)

Paper

Yuyang Dai, Yan Lin, Zhuohan Xie, Yuxia Wang
RealFin: How Well Do LLMs Reason About Finance When Users Leave Things Unsaid?
In: The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)

Paper Code