PETapter: Leveraging PET-style classification heads for modular few-shot parameter-efficient fine-tuning

Jonas Rieger, Mattes Ruckdeschel, Gregor Wiedemann


Anthology ID:
2025.konvens-1.29
Volume:
Proceedings of the 21st Conference on Natural Language Processing (KONVENS 2025): Long and Short Papers
Month:
September
Year:
2025
Address:
Hannover, Germany
Editors:
Christian Wartena, Ulrich Heid
Venue:
KONVENS
SIG:
Publisher:
HsH Applied Academics
Note:
Pages:
333–348
Language:
URL:
https://preview.aclanthology.org/corrections-2025-09/2025.konvens-1.29/
DOI:
Bibkey:
Cite (ACL):
Jonas Rieger, Mattes Ruckdeschel, and Gregor Wiedemann. 2025. PETapter: Leveraging PET-style classification heads for modular few-shot parameter-efficient fine-tuning. In Proceedings of the 21st Conference on Natural Language Processing (KONVENS 2025): Long and Short Papers, pages 333–348, Hannover, Germany. HsH Applied Academics.
Cite (Informal):
PETapter: Leveraging PET-style classification heads for modular few-shot parameter-efficient fine-tuning (Rieger et al., KONVENS 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/corrections-2025-09/2025.konvens-1.29.pdf