Ph.D. Student in Natural Language Processing
02.2024 - current
L3S Research Center, Leibniz University Hannover, Hannover, Germany
M.Sc. Computaional Linguistics
11.2018 - 03.2023
IMS, Departments of Computer Science, Faculty 5, University of Stuttgart, Stuttgart, Germany
M.A. Chinese Linguistics
08.2016 - 10.2018
Faculty of Arts and Humanities, University of Macau, Macau, China (Scholarship)
B.A. Chinese Language and Literature (Education)
09.2012 - 06.2016
Wuyi University, Jiangmen, China (an outstanding student leader in the top 2% and an outstanding graduate in the top 10%.)
Work Experience
Research Assistant
L3S Research Center, Leibniz University Hannover, Hannover, Germany
02.2024 - Current
Working in project Hybrid Intelligence through Interpretable AI (HybrInt)
emphasizing academic publications knowledge mining.
R&D NLU Language Specialist
Cerence GmbH, Aachen & Ulm, Germany (Remote)
10.2020 - 09.2022
Processed training/test data, developed a WPF annotation tool,
and enhanced dialogue system accuracy by 10% through error analysis.
Research Analyst Intern
E-Research & Solutions, Macau, China
12.2016 - 06.2017
Analyzed social media data for public opinion fine-grained sentiment analysis, contributed to writing reports & “Data Mining” brochures.
Teaching Assistant
University of Macao, Macao, China
01.2017 - 05.2017
Prepared materials, organized group discussions,
assisted in organizing conferences, and responsible for publicity work.
Publications
EviMap: Evidence-Grounded Hierarchical Topic Maps for Exploring Unlabeled Corpora
Zhiyin Tan, Changxu Duan,
ACM International Conference on Information and Knowledge Management (CIKM, Demo Paper, to appear).
Beyond Catalogue Counts: the Dataset Visibility Asymmetry in Low-Resource Multilingual NLP
Zhiyin Tan, Changxu Duan,
The 15th International Conference on Language Resources and Evaluation (LREC, Oral).
Diagnosing the Limits of Large Language Models for Structured Scientific Evidence Extraction
Zhiyin Tan, Jennifer D'Souza, Sören Auer,
International Journal on Digital Libraries (IJDL, extended version of the IRCDL 2026 paper, to appear).
Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis
⎡Best Paper Award⎦
Zhiyin Tan, Jennifer D'Souza,
the 22nd Conference on Information and Research Science Connecting to Digital and Library Science.
Multi-Disciplinary Dataset Discovery from Citation-Verified Literature Contexts
Zhiyin Tan, Changxu Duan,
the 25th ACM/IEEE Joint Conference on Digital Libraries (JCDL, Oral).
Semantically Orthogonal Framework for Citation Classification: Disentangling Intent and Content
Changxu Duan*, Zhiyin Tan*(*co-first),
the 29th International Conference on Theory and Practice of Digital Libraries (TPDL, Oral).
Toward purpose-oriented topic model evaluation enabled by large language models
Zhiyin Tan, Jennifer D'Souza,
International Journal on Digital Libraries, Volume 26, article number 23, 2025 (IJDL).
Bridging the Evaluation Gap: Leveraging Large Language Models for Topic Model Evaluation
Zhiyin Tan, Jennifer D'Souza,
the 21st Conference on Information and Research Science Connecting to Digital and Library Science.
LATEX Rainbow: Universal LATEX to PDF Document Semantic & Layout Annotation Framework
Changxu Duan, Zhiyin Tan, Sabine Bartsch,
the 2nd Workshop on Information Extraction from Scientific Publications at IJCNLP-AACL.
Applied Contrastive Learning to Fine-grained Entity Type Classification (Master's Thesis)
Text-based Personality Prediction
Zhiyin Tan,
Poster presented at the Machine Learning Summer School (MLSS 2021 Taipei).
The use of Cantonese Discourse Markers by Legislative Council Members in Hong Kong and Macau
⎡Excellent Award⎦
Zhiyin Tan,
Master's Thesis, preliminary results presented at the 4th Workshop on Innovations in Cantonese Linguistics (WICL-4).
A Comparative Study of Mandarin Pitch Range in Northern and Central Taiwan
Zhiyin Tan,
Research conducted during the National Taiwan University Summer+ Intensive Research Visiting Program.