Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency
cs.CL, cs.AI, cs.LG
Submitted: 2026-03-17
Updated: 2026-11-18
Terminology
Sources
- ECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge Transfer
- MultiLoKo: a multilingual local knowledge benchmark for LLMs spanning 31 languages
- Language-Specific Latent Process Hinders Cross-Lingual Performance
- Rethinking Cross-lingual Gaps from a Statistical Viewpoint
- GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
- OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
- Qwen3 Technical Report
- Beyond Benchmarks: Understanding Mixture-of-Experts Models through Internal Mechanisms
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data