4 papers
LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models
Nam V. Nguyen, Thong T. Doan, Luong Tran +2
Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as GPT-OSS, DeepSeek-V3, Llama-4, and Gem…
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
Huu Nguyen, Victor May, Harsh Raj +14
We present MixtureVitae, an open-access pretraining corpus built to minimize legal risk while providing strong downstream performance. MixtureVitae follows a permissive-first, risk…
CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition
Nam V. Nguyen, Huy Nguyen, Quang Pham +3
Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width. However, we argue that ef…
XCOMPS: A Multilingual Benchmark of Conceptual Minimal Pairs
Linyang He, Ercong Nie, Sukru Samet Dindar +10
We introduce XCOMPS in this work, a multilingual conceptual minimal pair dataset covering 17 languages. Using this dataset, we evaluate LLMs' multilingual conceptual understanding…