Refusal Direction is Universal Across Safety-Aligned Languages Paper • 2505.17306 • Published 27 days ago • 1
How Programming Concepts and Neurons Are Shared in Code Language Models Paper • 2506.01074 • Published 17 days ago • 3
Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models Paper • 2504.04264 • Published Apr 5 • 1
How Programming Concepts and Neurons Are Shared in Code Language Models Paper • 2506.01074 • Published 17 days ago • 3
Tracing Multilingual Factual Knowledge Acquisition in Pretraining Paper • 2505.14824 • Published 29 days ago • 4
A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation Paper • 2406.09881 • Published Jun 14, 2024
Decomposed Prompting: Unveiling Multilingual Linguistic Structure Knowledge in English-Centric Large Language Models Paper • 2402.18397 • Published Feb 28, 2024 • 1
Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers Paper • 2402.11700 • Published Feb 18, 2024 • 1
ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks Paper • 2401.16589 • Published Jan 29, 2024 • 1
Tracing Multilingual Factual Knowledge Acquisition in Pretraining Paper • 2505.14824 • Published 29 days ago • 4
Tracing Multilingual Factual Knowledge Acquisition in Pretraining Paper • 2505.14824 • Published 29 days ago • 4
Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models Paper • 2505.16538 • Published 28 days ago • 2