UrduMMLU is a new native-source MCQ benchmark for Urdu that reveals top LLMs reach only ~90% accuracy with large gaps on region-specific humanities content.
Crosslingual Generalization through Multitask Finetuning
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
TokAlign++ learns token alignments between LLM vocabularies from monolingual representations to enable faster adaptation, better text compression, and effective token-level distillation across 15 languages with minimal steps.
C-Mining automatically mines high-fidelity Culture Points from raw multilingual text by treating cross-lingual geometric isolation in embeddings as a quantifiable signal for cultural specificity, then uses them to synthesize better instruction data.
M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual, and long-document retrieval benchmarks.
Bucket-Level MOO reformulates multilingual fine-tuning as localized multi-objective optimization and proves it enforces a tighter Pareto stationarity condition while improving cross-lingual performance on four LLMs.
RSA on 7T fMRI during natural scene viewing identifies ventromedial and lateral occipitotemporal representational routes for scene context versus animate content, with differential alignment to vision and language models.
Lius improves LLM translation for Kupang Malay by 4-13 points over baselines via continual instruction tuning with dictionary-derived instructions.
citing papers explorer
-
Multilingual Fine-Tuning via Localized Gradient Conflict Resolution
Bucket-Level MOO reformulates multilingual fine-tuning as localized multi-objective optimization and proves it enforces a tighter Pareto stationarity condition while improving cross-lingual performance on four LLMs.