Showing 1–20 of 20 results
/ Date/ Name
Apr 12, 2020When Does Unsupervised Machine Translation Work?Jul 3, 2024How Does Quantization Affect Multilingual LLMs?Jun 28, 2024Understanding and Mitigating Language Confusion in LLMsOct 11, 2022IsoVec: Controlling the Relative Isomorphism of Word Embedding SpacesMay 27, 2025The Multilingual Divide and Its Impact on Global AI SafetyDec 4, 2024Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual EvaluationSep 26, 2021An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding SpacesJun 30, 2021On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine TranslationMay 23, 2024Aya 23: Open Weight Releases to Further Multilingual ProgressDec 20, 2022Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow TrainingOct 25, 2022Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal TransportApr 18, 2021Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space GeometryFeb 16, 2026Unlocking Reasoning Capability on Machine Translation in Large Language ModelsJul 3, 2023Improving Language Plasticity via Pretraining with Active ForgettingJul 2, 2024RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMsJan 17, 2023Learning a Formality-Aware Japanese Sentence RepresentationApr 24, 2025The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMsMay 21, 2025MAPS: A Multilingual Benchmark for Agent Performance and SecurityDec 5, 2024AL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal ArabicApr 1, 2025Command A: An Enterprise-Ready Large Language Model