1 citations · 1 across the 8 of their papers we have counts for
9 papers
Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning
Mehrnaz Mofakhami, Ananya Sahu, Alejandro R. Salamanca +5
Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: models primarily reason in Eng…
The Culture Funnel: You Can't Align What isn't in the Data
Ananya Sahu, Mehrnaz Mofakhami, Daniel D'Souza +3
Current cultural alignment approaches focus on inference-time interventions, assuming models already contain sufficient cultural knowledge. We argue modern LLM pipelines suffer fro…
A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
Leo Schwinn, Moritz Ladenburger, Tim Beyer +3
Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, thes…
Tiny Aya: Bridging Scale and Multilingual Depth
Alejandro R. Salamanca, Diana Abagyan, Daniel D'souza +23
Tiny Aya redefines what a small multilingual language model can achieve. Trained on 70 languages and refined through region-aware posttraining, it delivers state-of-the-art in tran…
A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens
David Dobre, Mehrnaz Mofakhami, Sophie Xhonneux +2
Many safety post-training methods for large language models (LLMs) are designed to modify the model's behaviour from producing unsafe answers to issuing refusals. However, such dis…
Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones
Mehrnaz Mofakhami, Reza Bayat, Ioannis Mitliagkas +2
Early Exiting (EE) is a promising technique for speeding up inference by adaptively allocating compute resources to data points based on their difficulty. The approach enables pred…