activity
20242026
collaborators

10 papers

cs.CL2026

LKValues: Aligning Large Language Models with Sri Lankan Societal Values

Nethmi Muthugala, Supryadi, Surangika Ranathunga +7

Value alignment of Large Language Models (LLMs) has been shown to be culturally biased toward Western norms. This results in the mishandling of local values in multilingual societi…

cs.CL2026

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…

cs.CL2026

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…

cs.CL2025

Making, not Taking, the Best of N

Ammar Khairi, Daniel D'souza, Marzieh Fadaee +1

Obtaining high-quality generations in modern LLMs has largely been framed as a selection problem: identifying a single winning generation from a diverse pool of N samples, the Best…

cs.CL2025

When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs

Ammar Khairi, Daniel D'souza, Ye Shen +2

Recent advancements in large language models (LLMs) have shifted focus toward scaling inference-time compute, improving performance without retraining the model. A common approach…

cs.CL2025

Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers

Daniel D'souza, Julia Kreutzer, Adrien Morisot +2

One of the most profound challenges of modern machine learning is performing well on the long-tail of rare and underrepresented features. Large general-purpose models are trained f…