Cross-Lingual Alignment for Decoder-Only Models using MoE Routers

arXiv:2610.01921 · cs.CL, cs.AI · Submitted 2026-10-01 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-10-01

Updated: 2026-10-02

Code: https://github.com/lucasbandarkar/xl_moe_

Terminology

• Alignment — 72× in this paper · explained in 1 episode
• Benchmark — 15× in this paper · explained in 2 episodes
• Contrastive Learning — 10× in this paper · explained in 5 episodes
• Cross-lingual Transfer — 7× in this paper · explained in 2 episodes
• Embeddings — 6× in this paper · explained in 2 episodes
• Representation Learning — 6× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 5× in this paper
• Steering — 4× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Abundance — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Activation Patching — 1× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Alignment Methods — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Information-Theoretic Framework — 1× in this paper · explained in 2 episodes
• Mixture-of-Experts (MoE) — 1× in this paper · explained in 7 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency
• Multilinguality in Hybrid Attention LLMs
• Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
• DeepSeek-V3 Technical Report
• MultiLoKo: a multilingual local knowledge benchmark for LLMs spanning 31 languages
• Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling
• Leveraging Routing Dynamics in Mixture-of-Experts Models for Efficient Language Adaptation
• Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation
• Language-Specific Latent Process Hinders Cross-Lingual Performance
• Improving Multilingual Language Models by Aligning Representations through Steering
• MTet: Multi-domain Translation for English and Vietnamese
• gpt-oss-120b & gpt-oss-20b Model Card
• Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech
• Representation Learning with Contrastive Predictive Coding
• Multilingual E5 Text Embeddings: A Technical Report
• Emu3: Next-Token Prediction is All You Need
• CLEAR: Contrastive Learning for Sentence Representation
• OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
• Qwen3 Technical Report
• Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering