multilingual-llm

Tag

Cards List
#multilingual-llm

Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations

arXiv cs.CL · 6d ago Cached

This paper investigates the structural sensitivity of multilingual large language models to semantics-preserving perturbations in Hindi and Malayalam, showing significant degradation in mathematical reasoning performance and introducing the IndicReStruct benchmark for evaluation.

0 favorites 0 likes
#multilingual-llm

An Investigation of Translationese in the Generations of Multilingual Large Language Models

arXiv cs.CL · 2026-08-19 Cached

This paper investigates whether text generated by multilingual large language models exhibits signs of translationese, and compares it to human-written translations to assess linguistic naturalness.

0 favorites 0 likes
#multilingual-llm

LLMs Get Smarter from Targeted Synthetic Multilingual Data

Hugging Face Daily Papers · 2026-08-16 Cached

HOTFIXR is a data generation framework that targets multilingual reasoning weaknesses in LLMs to improve cross-lingual performance using synthetic data without sacrificing overall capability.

0 favorites 0 likes
#multilingual-llm

Cross-Lingual Steering for Figurative Language Generation

arXiv cs.CL · 2026-06-01 Cached

This paper explores cross-lingual transfer of internal representations for figurative language generation in multilingual LLMs, showing that activation directions learned in one language can effectively steer generation in other languages.

0 favorites 0 likes
#multilingual-llm

Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Text: A Comparative Study

arXiv cs.CL · 2026-05-15 Cached

Benchmarks seven foundation models on Ukrainian legal text, finding tokenizer fertility varies 1.6×, few-shot prompting degrades performance, and cost-performance analysis shows NVIDIA Nemotron Super 3 outperforms larger models.

0 favorites 0 likes
#multilingual-llm

No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs

arXiv cs.CL · 2026-04-21 Cached

Researchers from National Taiwan University propose replacing fixed translation-based prompting strategies in multilingual LLMs with lightweight learned classifiers that route each instance to either native or translation-based prompting. Their analysis across 10 languages and 4 benchmarks shows no single strategy is universally optimal, with translation benefiting low-resource languages most, and the learned routing achieving statistically significant improvements over fixed strategies.

0 favorites 0 likes
← Back to home

Submit Feedback