Scholar
Mario Sanz-Guerrero
Google Scholar ID: OElovs8AAAAJ
Ph.D. Student, Johannes Gutenberg University Mainz
Citations & Impact
Citations
18
H-index
2
i10-index
1
Publications
10
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- 1. Papers 'Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs' and 'Molecular String Representation Preferences in Pretrained LLMs' accepted to EMNLP 2025; 2. Paper 'Reducing leads, enhancing wearable practicality: A comparative study of 3-lead vs. 12-lead ECG classification' accepted to the journal Medical Engineering & Physics; 3. Paper 'Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models' accepted to the 6th Workshop on Insights from Negative Results in NLP @ NAACL 2025; 4. Paper 'Asking Again and Again: Exploring LLM Robustness to Repeated Questions' available on arXiv; 5. Paper 'Credit Risk Meets Large Language Models: Building a Risk Indicator from Loan Descriptions in P2P Lending' accepted to the journal Inteligencia Artificial.
Research Experience
- 1. Research at NALA lab; 2. Worked as an AI engineer in the healthcare industry.
Education
- 1. PhD - Natural Language Processing, Johannes Gutenberg University Mainz, Supervisor: Katharina von der Wense; 2. MSc - Artificial Intelligence; 3. BSc - Computer Science.
Background
- Research Interests: Language Modeling & Emergent Abilities, LLM Calibration, Biomedical NLP. Brief Introduction: Mario is a PhD student in Natural Language Processing at Johannes Gutenberg University Mainz, supervised by Katharina von der Wense. He has completed his BSc in Computer Science and MSc in Artificial Intelligence. He has also worked as an AI engineer in the healthcare industry.
Miscellany
- Personal interests and hobbies not mentioned
Co-authors