Picture for David Stap

David Stap

Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?

Add code
Sep 27, 2024
Viaarxiv icon

Data Contamination Report from the 2024 CONDA Shared Task

Add code
Jul 31, 2024
Figure 1 for Data Contamination Report from the 2024 CONDA Shared Task
Figure 2 for Data Contamination Report from the 2024 CONDA Shared Task
Figure 3 for Data Contamination Report from the 2024 CONDA Shared Task
Figure 4 for Data Contamination Report from the 2024 CONDA Shared Task
Viaarxiv icon

The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities

Add code
May 30, 2024
Viaarxiv icon

How Far Can 100 Samples Go? Unlocking Overall Zero-Shot Multilingual Translation via Tiny Multi-Parallel Data

Add code
Jan 22, 2024
Viaarxiv icon

Multilingual k-Nearest-Neighbor Machine Translation

Add code
Oct 23, 2023
Viaarxiv icon

UvA-MT's Participation in the WMT23 General Translation Shared Task

Add code
Oct 15, 2023
Viaarxiv icon

Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lens

Add code
May 19, 2023
Viaarxiv icon

Towards a general purpose machine translation system for Sranantongo

Add code
Dec 13, 2022
Viaarxiv icon

Benchmarking Generalization via In-Context Instructions on 1,600+ Language Tasks

Add code
Apr 16, 2022
Figure 1 for Benchmarking Generalization via In-Context Instructions on 1,600+ Language Tasks
Figure 2 for Benchmarking Generalization via In-Context Instructions on 1,600+ Language Tasks
Figure 3 for Benchmarking Generalization via In-Context Instructions on 1,600+ Language Tasks
Figure 4 for Benchmarking Generalization via In-Context Instructions on 1,600+ Language Tasks
Viaarxiv icon

Conditional Image Generation and Manipulation for User-Specified Content

Add code
May 11, 2020
Figure 1 for Conditional Image Generation and Manipulation for User-Specified Content
Figure 2 for Conditional Image Generation and Manipulation for User-Specified Content
Figure 3 for Conditional Image Generation and Manipulation for User-Specified Content
Figure 4 for Conditional Image Generation and Manipulation for User-Specified Content
Viaarxiv icon