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 introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

This paper introduces robustness indicators to systematically analyze how multilingual text embedding model rankings change based on dataset composition and aggregation methods, revealing that only a…

The paper demonstrates that using English prompts causes large language models to prioritize globally dominant narratives over local cultural knowledge, even when local evidence is provided.

This paper investigates how LLMs handle multiple writing systems, finding that while they use shared latent representations, the model exhibits a structural bias that makes generating Latin script eas…

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 proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…

This paper systematically investigates the difficulty of Chinese Zero Pronouns (ZPs) for various LLMs, concluding that ZPs remain a significant and persistent challenge, with state-of-the-art models p…

The paper demonstrates that the AI-like style introduced by post-training alignment can be measured, localized, and causally removed using a novel ablation technique called PASTA.

The paper introduces a new benchmark for multi-target cross-lingual summarization (MTXLS) and proposes an activation steering method that significantly improves LLM performance by guiding the generati…

The paper audits six LLMs across four languages, finding that their gender stereotyping is significantly wider than human baselines and that cross-lingual translation fundamentally alters the nature o…

The paper investigates whether modestly sized open-source language models can grasp the semantics of rare Paired-Focus constructions, finding that understanding emerges later in training and correlate…

The paper introduces a multilingual benchmark (MentalMap) to test if LLMs build internal spatial world models from text, finding a universal 'L3 reasoning cliff' suggesting that text-only working memo…

The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from…

The paper proposes MACAT, a Multi-Agent Culture-Aware Translation framework, to selectively translate culture-loaded words in ancient Chinese texts, achieving superior performance over existing method…

The paper demonstrates that the internal signals governing figurative language generation are reusable across multiple languages, showing that a steering direction learned in one language can effectiv…

The paper develops a theoretically grounded framework for evaluating multilingual LLMs in Social Sciences and Humanities, moving beyond traditional NLP benchmarks to assess interpretive validity and c…

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…

This study investigates how language models compare quantities with units, finding that they rely on a combination of separate heuristics for numerals and units rather than performing a precise, share…