9 citations · 12 across the 8 of their papers we have counts for
4 papers · 1 filter
ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding
Zirui Wang, Yusen Hou, Shaofeng Liang +4
The explosive growth of large language models (LLMs) has created a heterogeneous and poorly documented ecosystem, making systematic model comparison increasingly important for prov…
On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment
Zirui Wang, Zachary C. Lipton, Yulia Tsvetkov
Modern multilingual models are trained on concatenated text from multiple languages in hopes of conferring benefits to each (positive transfer), with the most pronounced benefits a…
Efficient Meta Lifelong-Learning with Limited Memory
Zirui Wang, Sanket Vaibhav Mehta, Barnabás Póczos +1
Current natural language processing models work well on a single task, yet they often fail to continuously learn new tasks without forgetting previous ones as they are re-trained t…
Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework
Zirui Wang, Jiateng Xie, Ruochen Xu +3
Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks. There are two main paradigms for learning such represen…