The paper introduces XLGoBench, a synthetic benchmark of algorithmic tasks designed to detect persistent cross-lingual skill gaps in large language models.

The paper proposes MIMO, a two-stage framework that improves Multilingual Information Retrieval (MLIR) by stabilizing cross-lingual alignment and enhancing retrieval discrimination using a combination…

The paper proposes an unsupervised Reinforcement Learning approach that enforces cross-lingual self-consistency to significantly enhance the multilingual reasoning capabilities of large language model…

This paper introduces MMed-Bench-IR, a benchmark for multilingual medical retrieval in clinical settings, evaluating cross-lingual alignment, concept discrimination, and evidence retrieval.

The paper proposes a zero-shot cross-lingual method to estimate language model confidence by training a lightweight linear probe on one language and applying it directly to unseen, typologically diver…

This paper introduces SkMTEB, a comprehensive text embedding benchmark for Slovak, and develops efficient, locally-deployable Slovak embeddings.

The authors demonstrate that fine-tuning a two-stage retrieval system using synthetic data generated by large language models can significantly improve the performance of medical semantic search for c…

This paper investigates strategies to mitigate cross-lingual biases in Large Language Models and evaluates their effectiveness using a multilingual factual dataset.

The paper introduces and evaluates five parameter alignment strategies that significantly mitigate catastrophic forgetting when continually pretraining multilingual expert language models across multi…

The paper introduces MIDI, a novel multilingual dataset that embeds idioms in realistic sentence and conversational contexts across diverse resource levels, revealing that idiom comprehension is signi…

This paper presents a study on improving healthcare-domain translation for four low-resource languages using Arabic and Persian as pivots, and introduces three transfer strategies.

This study systematically analyzes strategies for creating reliable multilingual LLMs-as-a-judge, finding that fine-tuning smaller models with in-domain data is effective, while zero-shot evaluation w…

This paper introduces a pipeline to extract grammatical rules, example sentences, and lexicons from grammar books and generates synthetic parallel corpora for fine-tuning machine translation models on…

The paper introduces RA-MoE, a novel fine-tuning framework that leverages the internal routing structure of Mixture-of-Experts (MoE) models to improve performance on multilingual downstream tasks by a…

The paper introduces LAMAR, a language aware multilingual cross encoder for multilingual retrieval augmented generation, which prioritizes documents written in the same language as the query for langu…

The paper introduces Multi-Legal-Bench, a novel cross-jurisdictional benchmark evaluating LLMs on five standardized legal reasoning tasks across six diverse countries, demonstrating that cross-lingual…

The paper proposes an aggressive, parameter-efficient method to prune non-essential experts from Mixture-of-Experts (MoE) LLMs, significantly compressing the model while maintaining high machine trans…

The paper proposes Randomized YaRN, a training method that improves length generalization in large language models by exposing them to out-of-distribution positional representations during training on…