There are inconsistent conclusions about the impact of calibration data on Post-Training Quantization (PTQ) across studies, specifically regarding the factors that make the method effective, such as language that we explore in this work. We investigate this question by evaluating GPTQ and its mixed-precision variants across three low-bit settings, using language-targeted calibration sets across five language families. By evaluating performance across both perplexity and downstream tasks, we find that selecting an appropriate calibration language is generally beneficial, though model sensitivity varies with bit-width, target language, and task difficulty. We further show that mixed-precision techniques expand the representational capacity of low-bit models, occasionally allowing 2-bit models to approach 3-bit performance when paired with language-targeted calibration, while increased effective-bits remains small. Furthermore, we explore the correlation between these factors and observe that the calibration set sensitivity is influenced by different combinations of factors for each controlled variable, which can be explained by the downstream task results. Finally, while the benefit of language-targeted calibration transfers to sibling languages within the same family, the magnitude of this transfer does not reliably predicted by their closeness. Together, these findings show calibration data selection as a deliberate design choice in multilingual PTQ rather than an incidental one. Our code and result data can be accessed in https://github.com/rafifpriyo/multilingual-calibration-study.

Multilingual benchmarks rarely test reasoning over culturally grounded premises: translated datasets keep English-centric scenarios, while culture-first datasets often lack control over the reasoning required. We propose Macaron, a template-first benchmark that factorizes reasoning type and cultural aspect across question languages. Using 100 language-agnostic templates that cover 7 reasoning types, 22 cultural aspects, native annotators create scenario-aligned English and local-language multiple-choice questions, and systematically derived True/False questions. Macaron contains 11,862 instances spanning 20 countries/cultural contexts, 10 scripts, and 20 languages and dialects (including low-resource ones like Amharic, Yoruba, Zulu, Kyrgyz, and some Arabic dialects). In zero-shot evaluation of 21 multilingual LLMs, reasoning-mode models achieve the strongest performance (80.8% overall) and near-parity between English and local languages (∆MC = −1.3%), while open-weight models degrade substantially in local languages (∆MC = −6.8%) and often approach chance on T/F tasks. Culture-grounded mathematical and counting templates are consistently the hardest. The data can be accessed here https://huggingface.co/datasets/AlaaAhmed2444/Macaron.

Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic nature makes it difficult to isolate language-specific units from cross-lingual representations. To address this, we explore sparse autoencoders (SAEs) for their ability to learn monosemantic features that represent concrete and abstract concepts across languages in LLMs. While some of these features are language-independent, the presence of language-specific features remains underexplored. In this work, we introduce SAE-LAPE, a method based on feature activation probability, to identify language-specific features within the feed-forward network. We find that many such features predominantly appear in the middle to late layers of the model and are interpretable. These features influence the model’s multilingual performance and language output, and can be used for language identification with performance comparable to fastText, along with more interpretability. Our code and complete figures are available [here](https://github.com/LyzanderAndrylie/language-specific-features).

The rapid advancement of Large Language Models (LLMs) has necessitated more robust evaluation methods that go beyond static benchmarks, which are increasingly prone to data saturation and leakage. In this paper, we propose a dynamic benchmarking framework for evaluating multilingual and multicultural capabilities through the social deduction game Spyfall. In our setup, models must engage in strategic dialogue to either identify a secret agent or avoid detection, utilizing culturally relevant locations or local foods. Our results show that our game-based rankings are consistent with Chatbot Arena rankings on the overlapping model. However, we find a significant performance gap in non-English contexts: models are generally less proficient when handling locally specific entities and often struggle with rule-following or strategic integrity in non-English languages. We demonstrate that this game-based approach provides a scalable, leakage-resistant, and culturally nuanced alternative to traditional NLP benchmarks. The dataset (game history) and source code can be accessed here.

Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate their understanding of such knowledge, we introduce WorldCuisines, a massive-scale benchmark for multilingual and multicultural, visually grounded language understanding. This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date. It includes tasks for identifying dish names and their origins. We provide evaluation datasets in two sizes (12k and 60k instances) alongside a training dataset (1 million instances). Our findings show that while VLMs perform better with correct location context, they struggle with adversarial contexts and predicting specific regional cuisines and languages. To support future research, we release a knowledge base with annotated food entries and images along with the VQA data.

Pruning techniques have been studied to construct small models for efficiency, yet the effect of cross-lingual, which shows language performance transferability, is understudied in this field. In this work, we investigate cross-lingual effects in multilingual large language model compression using iterative pruning and recovery. We employ structured layer pruning with LoRA-based recovery and knowledge distillation, testing whether calibration languages different from target evaluation languages can preserve multilingual performance. Experiments on Qwen2.5-7B and Llama3.1-8B demonstrate that any recovery language consistently outperforms no-recovery baselines, with even low-resource languages like Swahili providing ~5% improvements. In contrast to expectations, dominant pretraining languages do not always yield the best results, where Indonesian achieves the highest performance in Llama3.1-8B, while Japanese performs the best in Qwen2.5-7B. Our findings reveal that cross-lingual calibration effectively maintains multilingual capabilities in the iterative pruning.

Language-specific neurons, units in LLMs that strongly correlate with individual languages have been shown to influence model behavior by deactivating them. However, their role in amplification remains underexplored.This work investigates the effect of amplifying language-specific neurons through interventions across 18 languages, including low-resource ones, using three models primarily trained in different languages. We compare amplification factors by their effectiveness in steering to the target language using a proposed Language Steering Shift (LSS) evaluation score, then evaluate it on downstream tasks: commonsense reasoning (XCOPA, XWinograd), knowledge (Include), and translation (FLORES). The optimal amplification steering factors effectively steer output toward nearly all tested languages. Intervention using this factor on downstream tasks improves self-language performance in some cases but generally degrades cross-language results. These findings highlight the effect of language-specific neurons in multilingual behavior, where amplification can be beneficial especially for low-resource languages, but provides limited advantage for cross-lingual transfer.

This paper describes our team’s submission for the Social Media Mining for Health (SMM4H) 2021 shared task. We participated in three subtasks: Classifying adverse drug effect, COVID-19 self-report, and COVID-19 symptoms. Our system is based on BERT model pre-trained on the domain-specific text. In addition, we perform data cleaning and augmentation, as well as hyperparameter optimization and model ensemble to further boost the BERT performance. We achieved the first rank in both classifying adverse drug effects and COVID-19 self-report tasks.

Ambiguity is a problem we frequently face in Natural Language Processing. Word Sense Disambiguation (WSD) is a task to determine the correct sense of an ambiguous word. However, research in WSD for Indonesian is still rare to find. The availability of English-Indonesian parallel corpora and WordNet for both languages can be used as training data for WSD by applying Cross-Lingual WSD method. This training data is used as an input to build a model using supervised machine learning algorithms. Our research also examines the use of Word Embedding features to build the WSD model.