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

This paper details the systematic construction and training of a high-performing Romanian Vision-Language Model (VLM), demonstrating that language-specific adaptation significantly boosts performance…

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

mcp-proto-okn is a Python server that facilitates natural language access to complex scientific knowledge graphs, simplifying cross-domain knowledge analysis for biomedical research.

The paper proposes EPIC, an efficient and parallel decoding framework that significantly speeds up the process of constraining diffusion language model outputs using Context-Free Grammars (CFG).

The paper quantitatively confirms the Currier A/B language distinction in the Voynich Manuscript, demonstrating it is governed by a higher-dimensional, context-dependent boolean switch rather than a s…

The paper introduces UA-Legal-Bench, a comprehensive Ukrainian legal reasoning benchmark built from a massive judicial corpus, demonstrating that LLM performance is highly task-dependent and that simp…

The paper introduces BEA-Dialogue+, an expanded 200-hour corpus for Hungarian conversational ASR, demonstrating that while larger data is challenging, specialized fine-tuning techniques significantly…

The paper introduces a diagnostic framework to decompose multilingual LLM performance variance, showing that language identity and model-benchmark interactions are key drivers of performance gaps.

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 quantifies the cost of privacy in language identification and generation using differentially private (DP) methods, finding that the cost is surprisingly mild, particularly absent under appr…

The study investigates the generalization of auto-generated natural-language labels for language model features, finding that while the underlying features show cross-lingual semantic consistency, the…

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 introduces prefix filters and an algorithm (Palla) to systematically learn and apply specific error patterns in Large Language Models, significantly improving constrained generation tasks li…

This study finds that when users do not specify a jurisdiction, the language used in the prompt strongly biases the LLM's response toward a specific national legal framework (U.S. for English, China f…

This paper comparatively analyzes two automatic label error detection methods, Confident Learning and Dataset Cartography, demonstrating that targeted data filtering significantly improves model perfo…

The paper introduces CARTE, a new benchmark designed to test how well large language models understand fine-grained, regionally differentiated knowledge across the 13 metropolitan regions of France, r…

The paper introduces a new quantitative metric, Contextual Alternative Choice (CAC), to rigorously test language models' syntactic and functional understanding of determiners, showing that current mod…

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 IndoBias, a dual-track, culturally-grounded benchmark to evaluate biases in LLMs across Indonesian and three local languages, revealing significant differences in bias patterns ac…