paper
Cross-Lingual Exploration for Parametric Knowledge
paperactiveprovisional
cross-lingual-exploration-for-parametric-knowledge-27918ae3·1 events·first seen 20h agoAliases: Cross-Lingual Exploration for Parametric Knowledge
More like this (12)
Contrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model ArchitecturesSame Lesson, Different Story: Cross-Lingual Reconstruction of Cultural Narratives in Large Language ModelsKnowledge-Graph Grounding Helps LLMs Only for Out-of-Training Knowledge: A Controlled Study on Clinical Question AnsweringThe Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language ModelsExploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language ModelsAdaptive Multi-Resolution Procedural Knowledge Compression for Large Language ModelsActionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model FamiliesWhen English Isn't the Best Teacher: Source Language Effects in Cross-Lingual In-Context LearningPrivileged On-Policy ExplorationThe Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMsEvaluation Awareness Is Not One Capability: Evidence from Open Language ModelsLatent Context Language Models
Recent events (1)
Cross-lingual prompting strategies unlock hidden parametric knowledge in LLMs
A new arXiv preprint investigates how cross-lingual prompting can surface factual knowledge that standard inference techniques fail to retrieve in multilingual LLMs. The authors identify four dimensions of cross-lingual exploration governing parametric knowledge retrieval and evaluate them on multilingual factual benchmarks across 17 typologically diverse languages. Results show cross-lingual exploration improves both factual recall and cross-lingual consistency, and is claimed to be a more compute-efficient approach than scaling native-language inference.