Hsien-chin Lin

Postdoc, Heinrich Heine University Düsseldorf

Joined

November 2021

Names

Hsien-chin Lin (Preferred)

Hsien-Chin Lin

Emails

****@hhu.de (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Postdoc

Heinrich Heine University Düsseldorf (hhu.de)

2024 – 2028

PhD student

Heinrich Heine University Düsseldorf (hhu.de)

2019 – 2024

MS student

National Taiwan University (ntu.edu.tw)

2014 – 2016

Advisors, Relations & Conflicts

PhD Advisor

Milica Gasic

2019 – 2024

Expertise

No areas of expertise listed

Publications

Prompt reinforcing for long-term planning of large language models
Hsien-chin Lin, Benjamin Matthias Ruppik, Carel van Niekerk, Chia-Hao Shen, Michael Heck, Nurul Lubis, Renato Vukovic, Shutong Feng, Milica Gasic
- Submitted to ICLR 2026
- Readers: Everyone
Less is More: Local Intrinsic Dimensions of Contextual Language Models
Benjamin Matthias Ruppik, Julius von Rohrscheidt, Carel van Niekerk, Michael Heck, Renato Vukovic, Shutong Feng, Hsien-chin Lin, Nurul Lubis, Bastian Rieck, Marcus Zibrowius, Milica Gasic
- NeurIPS 2025 poster
- Readers: Everyone
A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction
Carel van Niekerk, Christian Geishauser, Michael Heck, Shutong Feng, Hsien-Chin Lin, Nurul Lubis, Benjamin Matthias Ruppik, Renato Vukovic, Milica Gasic
- Trans. Assoc. Comput. Linguistics 2025
- Readers: Everyone
Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling
Michael Heck, Christian Geishauser, Nurul Lubis, Carel van Niekerk, Shutong Feng, Hsien-Chin Lin, Benjamin Matthias Ruppik, Renato Vukovic, Milica Gasic
- AAAI 2025
- Readers: Everyone
RLSF: Reinforcement Learning from Self-feedback for improved logical reasoning
Matthew Sutton, Carel van Niekerk, Renato Vukovic, Hsien-chin Lin, Milica Gasic
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Text as parameter: interactive prompt optimisation for large language models
Hsien-chin Lin, Chia-Hao Shen, Benjamin Matthias Ruppik, Carel van Niekerk, Michael Heck, Nurul Lubis, Renato Vukovic, Shutong Feng, Milica Gasic
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Local Topology Measures of Contextual Language Model Latent Spaces With Applications to Dialogue Term Extraction
Benjamin Matthias Ruppik, Michael Heck, Carel van Niekerk, Renato Vukovic, Hsien-Chin Lin, Shutong Feng, Marcus Zibrowius, Milica Gasic
- CoRR 2024
- Readers: Everyone
Learning With an Open Horizon in Ever-Changing Dialogue Circumstances
Christian Geishauser, Carel van Niekerk, Nurul Lubis, Hsien-Chin Lin, Michael Heck, Shutong Feng, Benjamin Matthias Ruppik, Renato Vukovic, Milica Gasic
- IEEE ACM Trans. Audio Speech Lang. Process. 2024
- Readers: Everyone
Local Topology Measures of Contextual Language Model Latent Spaces with Applications to Dialogue Term Extraction
Benjamin Matthias Ruppik, Michael Heck, Carel van Niekerk, Renato Vukovic, Hsien-Chin Lin, Shutong Feng, Marcus Zibrowius, Milica Gasic
- SIGDIAL 2024
- Readers: Everyone

View all 49 publications

Co-Authors

View all 27 co-authors