3 papers
cs.CL2026
A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar Books
Varun Ghat Ravikumar, Sina Ahmadi, Lena Jäger +1
Most endangered languages lack the parallel data required for machine translation, despite the existence of descriptive grammar books. We introduce a pipeline that uses large langu…
cs.CR2026
Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference Optimization
Lena S. Bolliger, Lena A. Jäger
Production LLMs receive instructions from sources with very different levels of trust, yet attend to every token with uniform architectural privilege. This is the structural vulner…
cs.CL2025
Leveraging In-Context Learning for Political Bias Testing of LLMs
Patrick Haller, Jannis Vamvas, Rico Sennrich +1
A growing body of work has been querying LLMs with political questions to evaluate their potential biases. However, this probing method has limited stability, making comparisons be…