Multilingual Language Model Evaluation

Ask about this topic

Overview

The field studies whether language models understand and respond reliably across languages, rather than assuming results in English transfer. Researchers build native-speaker-authored and translated benchmarks, use controlled prompt comparisons, and probe linguistic features such as morphology, pragmatics, and tokenization. Evaluations span reasoning, translation, tool use, safety, bias, and calibration, combining automatic metrics with human judgments and internal-model analyses. A central tension is that translation artifacts, evaluator bias, and aggregate scores can hide language-specific failures; performance remains uneven, especially for lower-resource languages and cultural contexts.

Latest papers

CardsList

488 papers69 papers in the last four weeks, up 41% on the four weeks before. 0.4% of all new papers.

Apr 25, 2026

IdiomX A Multilingual Benchmark for Idiom Understanding, Retrieval, and Interpretation

Idiomatic expressions remain a persistent challenge for natural language processing because their meanings are often non-compositional, context-dependent, and difficult to align across languages. Existing idiom resources are often limited in scale, contextual diversity, or multilingual coverage, restricting their utility for modern language models. We introduce IdiomX, a large-scale multilingual benchmark for idiom understanding, retrieval, and interpretation, constructed through a reproducible multi-stage pipeline combining lexical resource extraction, large-scale normalization, controlled large language model enrichment, and structured validation. The resulting dataset contains over 190K contextualized examples spanning 12K+ idioms, with aligned English, Arabic, and French semantic representations, idiomatic and literal usage labels, and rich linguistic metadata. Building on this resource, we define a unified four-task benchmark covering idiom detection, context-to-idiom retrieval, Arabic-to-English idiom retrieval, and idiom interpretation, extending evaluation from figurative recognition to semantic grounding and explainable meaning retrieval. Experiments show that contextual transformer models substantially improve idiom detection, while hybrid retrieval and reranking architectures significantly strengthen both monolingual and cross-lingual idiom retrieval. Results further demonstrate that idiom interpretation can be effectively modeled as a semantic retrieval task, introducing interpretability as a complementary benchmark dimension. Overall, IdiomX provides a scalable benchmark for studying idiomatic language as a progression from detection to retrieval and semantic interpretation, and offers a modular framework extensible to additional languages and figurative reasoning tasks

Ayman Ali Sharara

MSc Data Science & Machine Learning (SPOC S21) Data ScienceTech Institute (DSTI)

Figurative Language UnderstandingMultilingual Language Model EvaluationMultilingual IR
AskPDF
Apr 24, 2026

Multilingual Refusal Alignment for Safer Large Language Models

As Large Language Models (LLMs) are deployed globally, ensuring their safety and alignment across multiple languages becomes paramount. However, safety behaviors often vary unpredictably between languages, posing significant challenges for consistent and ethical AI. In this work, we systematically investigate the dynamics of multilingual alignment, exploring whether single-language alignment transfers cross-lingually, how language consistency is preserved during training, and the resulting trade-offs with general knowledge capabilities. We introduce RefusEU, a novel refusal alignment dataset covering 12 European languages, including a dedicated test set for evaluating current state-of-the-art models. Our controlled Direct Preference Optimization (DPO) experiments provide two key insights: aligning models exclusively in English is insufficient to ensure cross-lingual safety, even for the same harm categories, whereas training on multilingual datasets can improve safety without degrading general performance, as measured by the Global MMLU benchmark.

Aleksandra Krasnodębska, Wojciech Kusa, Aldo Lipani

NASK National Research Institute, Warsaw, Poland · University College London, London, UK

Multilingual Language Model EvaluationLLM AlignmentLLM Safety AlignmentCross-Lingual Consistency in Language ModelsCross-Lingual Transfer
AskPDF
Apr 23, 2026

Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs

LLMs have been showing limitations when it comes to cultural coverage and competence, and in some cases show regional biases such as amplifying Western and Anglocentric viewpoints. While there have been works analysing the cultural capabilities of LLMs, there has not been specific work on highlighting LLM regional preferences when it comes to cultural-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ). The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan. Moveover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs and show less inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training.

Joseba Fernandez de Landa, Carla Perez-Almendros, Jose Camacho-Collados

HiTZ Center - Ixa, University of the Basque Country EHU · Cardiff University

Multilingual Language Model EvaluationCultural Bias in Language ModelsLanguage Model Bias EvaluationCultural Knowledge in Language Models
AskPDF
Apr 23, 2026

MKJ at SemEval-2026 Task 9: A Comparative Study of Generalist, Specialist, and Ensemble Strategies for Multilingual Polarization

We present a systematic study of multilingual polarization detection across 22 languages for SemEval-2026 Task 9 (Subtask 1), contrasting multilingual generalists with language-specific specialists and hybrid ensembles. While a standard generalist like XLM-RoBERTa suffices when its tokenizer aligns with the target text, it may struggle with distinct scripts (e.g., Khmer, Odia) where monolingual specialists yield significant gains. Rather than enforcing a single universal architecture, we adopt a language-adaptive framework that switches between multilingual generalists, language-specific specialists, and hybrid ensembles based on development performance. Additionally, cross-lingual augmentation via NLLB-200 yielded mixed results, often underperforming native architecture selection and degrading morphologically rich tracks. Our final system achieves an overall macro-averaged F1 score of 0.796 and an average accuracy of 0.826 across all 22 tracks. Code and final test predictions are publicly available at: https://github.com/Maziarkiani/SemEval2026-Task9-Subtask1-Polarization.

Maziar Kianimoghadam Jouneghani

University of Turin

Multilingual Language Model EvaluationLanguage Model EnsemblesCross-Lingual TransferMultilingual Text Classification
AskPDF
Apr 22, 2026

RespondeoQA: a Benchmark for Bilingual Latin-English Question Answering

We introduce a benchmark dataset for question answering and translation in bilingual Latin and English settings, containing about 7,800 question-answer pairs. The questions are drawn from Latin pedagogical sources, including exams, quizbowl-style trivia, and textbooks ranging from the 1800s to the present. After automated extraction, cleaning, and manual review, the dataset covers a diverse range of question types: knowledge- and skill-based, multihop reasoning, constrained translation, and mixed language pairs. To our knowledge, this is the first QA benchmark centered on Latin. As a case study, we evaluate three large language models -- LLaMa 3, Qwen QwQ, and OpenAI's o3-mini -- finding that all perform worse on skill-oriented questions. Although the reasoning models perform better on scansion and literary-device tasks, they offer limited improvement overall. QwQ performs slightly better on questions asked in Latin, but LLaMa3 and o3-mini are more task dependent. This dataset provides a new resource for assessing model capabilities in a specialized linguistic and cultural domain, and the creation process can be easily adapted for other languages. The dataset is available at: https://github.com/slanglab/RespondeoQA

Marisa Hudspeth, Patrick J. Burns, Brendan O'Connor

Manning College of Information & Computer Sciences, University of Massachusetts Amherst · Institute for the Study of the Ancient World, New York University

Multilingual Language Model EvaluationMultilingual QALow-Resource Language ProcessingMachine Translation
AskPDF
Apr 22, 2026

The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models

Evaluating the multilingual and multicultural capabilities of Large Language Models (LLMs) is essential for their global utility. However, current benchmarks face three critical limitations: (1) fragmented evaluation dimensions that often neglect deep cultural nuances; (2) insufficient language coverage in subjective tasks relying on low-quality machine translation; and (3) shallow analysis that lacks diagnostic depth beyond simple rankings. To address these, we introduce GaoYao, a comprehensive benchmark with 182.3k samples, 26 languages and 51 nations/areas. First, GaoYao proposes a unified framework categorizing evaluation tasks into three cultural layers (General Multilingual, Cross-cultural, Monocultural) and nine cognitive sub-layers. Second, we achieve native-quality expansion by leveraging experts to rigorously localize subjective benchmarks into 19 languages and synthesizing cross-cultural test sets for 34 cultures, surpassing prior coverage by up to 111%. Third, we conduct an in-depth diagnostic analysis on 20+ flagship and compact LLMs. Our findings reveal significant geographical performance disparities and distinct gaps between tasks, offering a reliable map for future work. We release the benchmark (https://github.com/lunyiliu/GaoYao).

Yilun Liu, Chunguang Zhao, Mengyao Piao +14

Huawei, China · Fudan University, China

Multilingual Language Model EvaluationLLM EvaluationCross-Cultural Language Model EvaluationCultural Knowledge in Language Models
AskPDF
Apr 21, 2026

Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs

Multilingual large language models (LLMs) have minimized the fluency gap between languages. This advancement, however, exposes models to the risk of biased behavior, as knowledge and norms may propagate across languages. In this work, we aim to quantify models' inter- and intra-lingual biases, via their ability to answer locale-ambiguous questions. To this end, we present LocQA, a test set containing 2,156 questions in 12 languages, referring to various locale-dependent facts such as laws, dates, and measurements. The questions do not contain indications of the locales they relate to, other than the querying language itself. LLMs' responses to LocQA locale-ambiguous questions thus reveal models' implicit priors. We used LocQA to evaluate 32 models, and detected two types of structural biases. Inter-lingually, we show a global bias towards answers relevant to the US-locale, even when models are asked in languages other than English. Moreover, we discovered that this global bias is exacerbated in models that underwent instruction tuning, compared to their base counterparts. Intra-lingually, we show that when multiple locales are relevant for the same language, models act as demographic probability engines, prioritizing locales with larger populations. Taken together, insights from LocQA may help in shaping LLMs' desired local behavior, and in quantifying the impact of various training phases on different kinds of biases.

Guy Mor-Lan, Omer Goldman, Matan Eyal +6

GGoogle Research · BBar-Ilan University · CUniversity of Cambridge +1

Multilingual Language ModelsMultilingual Language Model EvaluationMultilingual QALanguage Model Bias EvaluationLinguistic Bias in Language Models
AskPDF
Apr 21, 2026

CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks

Large language models (LLMs) are now deployed worldwide, inspiring a surge of benchmarks that measure their multilingual and multicultural abilities. However, these benchmarks prioritize generic language understanding or superficial cultural trivia, leaving the evaluation of grounded tasks -- where models must reason within real-world, context-rich scenarios -- largely unaddressed. To fill this gap, we present CulturALL, a comprehensive and challenging benchmark to assess LLMs' multilingual and multicultural competence on grounded tasks. CulturALL is built via a human--AI collaborative framework: expert annotators ensure appropriate difficulty and factual accuracy, while LLMs lighten the manual workload. By incorporating diverse sources, CulturALL ensures comprehensive scenario coverage. Each item is carefully designed to present a high level of difficulty, making CulturALL challenging. CulturALL contains 2,610 samples in 14 languages from 51 regions, distributed across 16 topics to capture the full breadth of grounded tasks. Experiments show that the best LLM achieves 44.48% accuracy on CulturALL, underscoring substantial room for improvement.

Peiqin Lin, Chenyang Lyu, Wenjiang Luo +22

Alibaba Group · Beijing Language and Culture University · LMU Munich +6

Multilingual Language Model EvaluationLLM EvaluationLLM GroundingEvidence-Grounded ReasoningCross-Cultural Language Model EvaluationCultural Knowledge in Language Models
AskPDF
Apr 20, 2026

MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation

While multilingual large language models (LLMs) perform well on high-level tasks like translation and question answering, their ability to handle grammatical gender and morphological agreement remains underexplored. In morphologically rich languages, gender influences verb conjugation, pronouns, and even first-person constructions with explicit and implicit mentions of gender. We introduce MORPHOGEN, a morphologically grounded large-scale benchmark dataset for evaluating gender-aware generation in three typologically diverse grammatically gendered languages: French, Arabic, and Hindi. The core task, GENFORM, requires models to rewrite a first-person sentence in the opposite gender while preserving its meaning and structure. We construct a high-quality synthetic dataset spanning these three languages and benchmark 15 popular multilingual LLMs (2B-70B) on their ability to perform this transformation. Our results reveal significant gaps and interesting insights into how current models handle morphological gender. MORPHOGEN provides a focused diagnostic lens for gender-aware language modeling and lays the groundwork for future research on inclusive and morphology-sensitive NLP.

Mehul Agarwal, Aditya Aggarwal, Arnav Goel +2

SBILab, Indraprastha Institute of Information Technology Delhi

Multilingual Language Model EvaluationText Generation
AskPDF
Apr 20, 2026

MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval

Mathematical problem solving remains a challenging test of reasoning for large language and multimodal models, yet existing benchmarks are limited in size, language coverage, and task diversity. We introduce MathNet, a high-quality, large-scale, multimodal, and multilingual dataset of Olympiad-level math problems together with a benchmark for evaluating mathematical reasoning in generative models and mathematical retrieval in embedding-based systems. MathNet spans 47 countries, 17 languages, and two decades of competitions, comprising 30,676 expert-authored problems with solutions across diverse domains. In addition to the core dataset, we construct a retrieval benchmark consisting of mathematically equivalent and structurally similar problem pairs curated by human experts. MathNet supports three tasks: (i) Problem Solving, (ii) Math-Aware Retrieval, and (iii) Retrieval-Augmented Problem Solving. Experimental results show that even state-of-the-art reasoning models (78.4% for Gemini-3.1-Pro and 69.3% for GPT-5) remain challenged, while embedding models struggle to retrieve equivalent problems. We further show that retrieval-augmented generation performance is highly sensitive to retrieval quality; for example, DeepSeek-V3.2-Speciale achieves gains of up to 12%, obtaining the highest scores on the benchmark. MathNet provides the largest high-quality Olympiad dataset together with the first benchmark for evaluating mathematical problem retrieval, and we publicly release both the dataset and benchmark at https://mathnet.mit.edu.

Shaden Alshammari, Kevin Wen, Abrar Zainal +5

MIT · HUMAIN · Individual Researcher +1

Mathematical Reasoning BenchmarksMultilingual Language Model EvaluationInformation RetrievalRAG EvaluationMultimodal Model EvaluationLLM Mathematical Reasoning
AskPDF
Apr 20, 2026

Do LLMs Use Cultural Knowledge Without Being Told? A Multilingual Evaluation of Implicit Pragmatic Adaptation

Many benchmarks show that large language models can answer direct questions about culture. We study a different question: do they also change how they speak when culture is only implied by the situation? We evaluate 60 culturally grounded conversational scenarios across five languages in three conditions: a neutral baseline (Prompt A), an explicit cultural instruction (Prompt B), and implicit situational cueing (Prompt C). We score responses on 12 pragmatic features covering deference to authority, individual-versus-group framing, and uncertainty management. We define Pragmatic Context Sensitivity (PCS) as the fraction of the Prompt A->B shift that reappears under Prompt A->C. Across four deployed LLMs and five languages (English, German, Hindi, Nepali, Urdu), the primary stable-only PCS mean is 0.196 (SD = 0.113), indicating that the models recover only about one-fifth of the pragmatic shift they can produce when instructed explicitly. Transfer is strongest for authority-related cues (0.299) and weakest for individual-versus-group framing (0.120). Uncertainty-related behaviour is mixed: hedging density exhibits negative explicit gaps in all five languages, suggesting that alignment training actively suppresses the target behaviour. Because Hindi and Urdu share core grammar yet index distinct cultural communities, we use them as a natural control; a paired analysis finds no reliable baseline difference (t = 0.96, p = 0.339, dz = 0.06), suggesting that models respond primarily to linguistic structure rather than to the cultural associations a language carries. We argue that multilingual cultural pragmatics is an explicit-versus-implicit deployment problem, not only a factual knowledge problem.

Mehwish Nasim, Sanjeevan Selvaganapathy, Neel Ganapathi Sabhahit +6

1Network Analysis and Social Influence Modelling (NASIM) Lab · 3Computational Social Science & Systems Analysis University of Münster · School of Computing Macquarie University

Multilingual Language ModelsMultilingual Language Model EvaluationCultural Bias in Language ModelsCultural Knowledge in Language Models
AskPDF
Apr 18, 2026

BIASEDTALES-ML: A Multilingual Dataset for Analyzing Narrative Attribute Distributions in LLM-Generated Stories

Large Language Models (LLMs) are increasingly used to generate narrative content, including children's stories, which play an important role in social and cultural learning. Despite growing interest in AI safety and alignment, most existing evaluations focus primarily on English, leaving the cross-lingual generalization of aligned behavior underexplored. In this work, we introduce BiasedTales-ML, a large-scale parallel corpus of approximately 350,000 children's stories generated across eight typologically and culturally diverse languages using a full-permutation prompting design. We propose a structured generator-extractor pipeline and a multi-dimensional distributional analysis framework to examine how narrative attributes vary across languages, models, and social conditions. Our analysis reveals substantial cross-lingual variability in narrative generation patterns, indicating that distributions observed in English do not always exhibit similar characteristics in other languages, particularly in lower-resource settings. At the narrative level, we identify recurring structural patterns involving character roles, settings, and thematic emphasis, which manifest differently across linguistic contexts. These findings highlight the limitations of English-centric evaluation for characterizing socially grounded narrative generation in multilingual settings. We release the dataset, code, and an interactive visualization tool to support future research on multilingual narrative analysis and evaluation.

Yuxuan Ouyang, yingfeng luo, JingBo Zhu +1

School of Computer Science and Engineering, Northeastern University, Shenyang, China · NiuTrans Research, Shenyang, China

Multilingual Language Model EvaluationSocial Bias in Language ModelsCultural Bias in Language ModelsText Generation
AskPDF
Apr 18, 2026

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

Translation-based prompting is widely used in multilingual LLMs, yet its effectiveness varies across languages and tasks. We evaluate prompting strategies across ten languages of different resource levels and four benchmarks. Our analysis shows that no single strategy is universally optimal. Translation strongly benefits low-resource languages even when translation quality is imperfect, high-resource languages gain little, and prompt-based self-routing underperforms explicit translation. Motivated by these findings, we formulate prompting strategy selection as a learned decision problem and introduce lightweight classifiers that predict whether native or translation-based prompting is optimal for each instance. The classifiers achieve statistically significant improvements over fixed strategies across four benchmarks and generalize to unseen task formats not observed during training. Further analysis reveals that language resource level, rather than translation quality alone, determines when translation is beneficial.

Wei-Chi Wu, Sheng-Lun Wei, Hen-Hsen Huang +1

Department of Computer Science and Information Engineering, National Taiwan University, Taiwan · Institute of Information Science, Academia Sinica, Taiwan · AI Research Center (AINTU), National Taiwan University, Taiwan

Multilingual Language Model EvaluationLLM PromptingLow-Resource Language ProcessingPrompt Engineering
AskPDF
Apr 17, 2026

No Universal Courtesy: A Cross-Linguistic, Multi-Model Study of Politeness Effects on LLMs Using the PLUM Corpus

This paper explores the response of Large Language Models (LLMs) to user prompts with different degrees of politeness and impoliteness. The Politeness Theory by Brown and Levinson and the Impoliteness Framework by Culpeper form the basis of experiments conducted across three languages (English, Hindi, Spanish), five models (Gemini-Pro, GPT-4o Mini, Claude 3.7 Sonnet, DeepSeek-Chat, and Llama 3), and three interaction histories between users (raw, polite, and impolite). Our sample consists of 22,500 pairs of prompts and responses of various types, evaluated across five levels of politeness using an eight-factor assessment framework: coherence, clarity, depth, responsiveness, context retention, toxicity, conciseness, and readability. The findings show that model performance is highly influenced by tone, dialogue history, and language. While polite prompts enhance the average response quality by up to ~11% and impolite tones worsen it, these effects are neither consistent nor universal across languages and models. English is best served by courteous or direct tones, Hindi by deferential and indirect tones, and Spanish by assertive tones. Among the models, Llama is the most tone-sensitive (11.5% range), whereas GPT is more robust to adversarial tone. These results indicate that politeness is a quantifiable computational variable that affects LLM behaviour, though its impact is language- and model-dependent rather than universal. To support reproducibility and future work, we additionally release PLUM (Politeness Levels in Utterances, Multilingual), a publicly available corpus of 1,500 human-validated prompts across three languages and five politeness categories, and provide a formal supplementary analysis of six falsifiable hypotheses derived from politeness theory, empirically assessed against the dataset.

Hitesh Mehta, Arjit Saxena, Garima Chhikara +1

Department of Computer Science Engineering, Delhi Technological University, New Delhi, India · Department of Electronics and Communication Engineering, Delhi Technological University, New Delhi, India

Multilingual Language Model EvaluationLLM EvaluationLanguage Model Robustness
AskPDF
Apr 17, 2026

Optimizing Korean-Centric LLMs via Token Pruning

This paper presents a systematic benchmark of state-of-the-art multilingual large language models (LLMs) adapted via token pruning - a compression technique that eliminates tokens and embedding parameters corresponding to languages irrelevant to the target application. Focusing on Korean-centric natural language processing (NLP) tasks, we evaluate architectures including Qwen3, Gemma-3, Llama-3, and Aya across three vocabulary configurations: Original, English-Korean (EnKo), and English-Korean-Chinese (EnKoZh). Performance is assessed using established benchmarks for general aptitude, cultural literacy, instruction following, and machine translation. Our findings indicate that token pruning significantly improves generation stability by eliminating language confusion, and in the case of machine translation, frequently enhances performance on Korean-specific tasks. While instruction-following capabilities display architecture-dependent variance linked to latent cross-lingual representations, the significant reduction in vocabulary size validates token pruning as a highly effective optimization strategy for memory-constrained, domain-specific deployments, despite modest gains in inference latency.

Hoyeol Kim, Hyeonwoo Kim

College of Computing · Independent Researcher

Multilingual Language Model EvaluationLLM PruningLLM CompressionLanguage Modeling
AskPDF
Apr 16, 2026

Brain Score Tracks Shared Properties of Languages: Evidence from Many Natural Languages and Structured Sequences

Recent breakthroughs in language models (LMs) using neural networks have raised the question: how similar are these models' processing to human language processing? Results using a framework called Brain Score (BS) -- predicting fMRI activations during reading from LM activations -- have been used to argue for a high degree of similarity. To understand this similarity, we conduct experiments by training LMs on various types of input data and evaluate them on BS. We find that models trained on various natural languages from many different language families have very similar BS performance. LMs trained on other structured data -- the human genome, Python, and pure hierarchical structure (nested parentheses) -- also perform reasonably well and close to natural languages in some cases. These findings suggest that BS can highlight language models' ability to extract common structure across natural languages, but that the metric may not be sensitive enough to allow us to infer human-like processing from a high BS score alone.

Jingnong Qu, Ashvin Ranjan, Shane Steinert-Threlkeld

University of Washington

Multilingual Language Model EvaluationLanguage Modeling
AskPDF
Apr 15, 2026

MARCA: A Checklist-Based Benchmark for Multilingual Web Search

Large language models (LLMs) are increasingly used as sources of information, yet their reliability depends on the ability to search the web, select relevant evidence, and synthesize complete answers. While recent benchmarks evaluate web-browsing and agentic tool use, multilingual settings, and Portuguese in particular, remain underexplored. We present MARCA, a bilingual (English and Portuguese) benchmark for evaluating LLMs on web-based information seeking. MARCA consists of 52 manually authored multi-entity questions, paired with manually validated checklist-style rubrics that explicitly measure answer completeness and correctness. We evaluate 14 models under two interaction settings: a Basic framework with direct web search and scraping, and an Orchestrator framework that enables task decomposition via delegated subagents. To capture stochasticity, each question is executed multiple times and performance is reported with run-level uncertainty. Across models, we observe large performance differences, find that orchestration often improves coverage, and identify substantial variability in how models transfer from English to Portuguese. The benchmark is available at https://github.com/maritaca-ai/MARCA

Thales Sales Almeida, Giovana Kerche Bonás, Ramon Pires +6

Maritaca AI · Jusbrasil

LLM EvaluationMultilingual Language Model EvaluationMultilingual QA
AskPDF
Apr 15, 2026

EuropeMedQA Study Protocol: A Multilingual, Multimodal Medical Examination Dataset for Language Model Evaluation

While Large Language Models (LLMs) have demonstrated high proficiency on English-centric medical examinations, their performance often declines when faced with non-English languages and multimodal diagnostic tasks. This study protocol describes the development of EuropeMedQA, the first comprehensive, multilingual, and multimodal medical examination dataset sourced from official regulatory exams in Italy, France, Spain, and Portugal. Following FAIR data principles and SPIRIT-AI guidelines, we describe a rigorous curation process and an automated translation pipeline for comparative analysis. We evaluate contemporary multimodal LLMs using a zero-shot, strictly constrained prompting strategy to assess cross-lingual transfer and visual reasoning. EuropeMedQA aims to provide a contamination-resistant benchmark that reflects the complexity of European clinical practices and fosters the development of more generalizable medical AI.

Francesco Andrea Causio, Vittorio De Vita, Olivia Riccomi +17

Section of Hygiene, University Department of Life Sciences and Public Health, Università Cattolica del Sacro Cuore, Rome, Italy · Società Italiana Intelligenza Artificiale in Medicina (SIIAM), Rome, Italy · NSBproject, Mantova, Italy +8

Multilingual Language Model EvaluationMultilingual VLM EvaluationBiomedical QAMultimodal QACross-Lingual Transfer
AskPDF
Apr 15, 2026

IndicDB -- Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages

While Large Language Models (LLMs) have significantly advanced Text-to-SQL performance, existing benchmarks predominantly focus on Western contexts and simplified schemas, leaving a gap in real-world, non-Western applications. We present IndicDB, a multilingual Text-to-SQL benchmark for evaluating cross-lingual semantic parsing across diverse Indic languages. The relational schemas are sourced from open-data platforms, including the National Data and Analytics Platform (NDAP) and the India Data Portal (IDP), ensuring realistic administrative data complexity. IndicDB comprises 20 databases across 237 tables. To convert denormalized government data into rich relational structures, we employ an iterative three-agent framework (Architect, Auditor, Refiner) to ensure structural rigor and high relational density (11.85 tables per database; join depths up to six). Our pipeline is value-aware, difficulty-calibrated, and join-enforced, generating 15,617 tasks across English, Hindi, and five Indic languages. We evaluate cross-lingual semantic parsing performance of state-of-the-art models (DeepSeek v3.2, MiniMax 2.7, LLaMA 3.3, Qwen3) across seven linguistic variants. Results show a 9.00% performance drop from English to Indic languages, revealing an "Indic Gap" driven by harder schema linking, increased structural ambiguity, and limited external knowledge. IndicDB serves as a rigorous benchmark for multilingual Text-to-SQL. Code and data: https://anonymous.4open.science/r/multilingualText2Sql-Indic--DDCC/

Aviral Dawar, Roshan Karanth, Vikram Goyal +1

Independent Researcher · BITS Pilani, Pilani, India · IIIT Delhi, New Delhi, India

Text-to-SQLMultilingual Language Model EvaluationLow-Resource Language ProcessingRelational Databases
AskPDF
Apr 14, 2026

Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss

Multilingual benchmarks guide the development of frontier models. Yet multilingual evaluations reported by frontier models are structured similar to popular reasoning and knowledge benchmarks, but across many languages. We show such benchmarks, and consequently multilingual evaluations, measure mathematical reasoning and factual recall, not multilingual proficiency. For example, thinking variants dramatically outperform instruct variants on these benchmarks, yet often perform worse on real-world multilingual tasks, such as LMArena. We propose a simple alternative: evaluate multilingual capability via round-trip translation. Given text in a source language, translate it to a target language and back; semantic gaps between the original and result expose failures in multilingual generation capabilities. Round-trip translation correlates almost perfectly (\r{ho} = 0.94) with user ratings on LMArena with our benchmark, requires no human reference translations, and does not require a more capable multilingual judge than tested models. Lastly, we introduce Lost in Translation (LiT), a challenging round-trip translation benchmark spanning widely spoken languages worldwide, for realistic evaluation of multilingual frontier models.

Ronald Skorobogat, Ameya Prabhu, Matthias Bethge

Tübingen AI Center, University of Tübingen

Multilingual Language Model EvaluationLanguage Model Generation EvaluationMT Evaluation
AskPDF
Apr 14, 2026

Universal NER v2: Towards a Massively Multilingual Named Entity Recognition Benchmark

While multilingual language models promise to bring the benefits of LLMs to speakers of many languages, gold-standard evaluation benchmarks in most languages to interrogate these assumptions remain scarce. The Universal NER project, now entering its fourth year, is dedicated to building gold-standard multilingual Named Entity Recognition (NER) benchmark datasets. Inspired by existing massively multilingual efforts for other core NLP tasks (e.g., Universal Dependencies), the project uses a general tagset and thorough annotation guidelines to collect standardized, cross-lingual annotations of named entity spans. The first installment (UNER v1) was released in 2024, and the project has continued and expanded since then, with various organizers, annotators, and collaborators in an active community.

Terra Blevins, Stephen Mayhew, Marek Šuppa +11

Northeastern University, USA · Duolingo, USA · Comenius University Bratislava, Slovakia +10

Named Entity RecognitionMultilingual Language Model Evaluation
AskPDF
Apr 13, 2026

MIXAR: Scaling Autoregressive Pixel-based Language Models to Multiple Languages and Scripts

Pixel-based language models are gaining momentum as alternatives to traditional token-based approaches, promising to circumvent tokenization challenges; however, existing models remain English-centric and are hard to train as generators. This paper introduces MIXAR, the first generative multilingual pixel-based language model, pretrained on eight high-resource languages spanning Latin and CJK scripts and scaled up to 0.5B parameters. Although pretrained on high-resource languages only, MIXAR generalizes to unseen low-resource languages better than a tokenizer-based model pretrained on the same corpus, with its largest gains on the scripts most distant from the pretraining mix, taking a step toward more equitable language technology. To make free generation work in pixel space, MIXAR replaces the notoriously unstable adversarial training stage of prior pixel-based models with a GRPO-based reinforcement-learning stage that rewards the model on its own free-running generations: it proves more stable and multiplies free-generation accuracy by up to 2.3x on multilingual benchmarks. Finally, MIXAR performs on par with comparable tokenizer-based models on discriminative benchmarks, improves consistently with scale, and withstands orthographic attacks more gracefully than tokenizer-based models. Code and models are available at https://github.com/april-tools/mixar.

Chen Hu, Yintao Tai, Antonio Vergari +2

School of Informatics, University of Edinburgh

Multilingual Language ModelsAutoregressive Language ModelingMultilingual Language Model EvaluationLanguage Model Robustness
AskPDF
Apr 13, 2026

Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation

Synthesizing supervised finetuning (SFT) data from language models (LMs) to teach smaller models multilingual tasks has become increasingly common. However, teacher model selection is often ad hoc, typically defaulting to the largest available option, even though such models may have significant capability gaps in non-English languages. This practice can result in poor-quality synthetic data and suboptimal student downstream performance. In this work, we systematically characterize what makes an effective multilingual teacher. We combine intrinsic measures of data quality with extrinsic student model performance in a metric we call Polyglot Score. We evaluate 10 LMs across 6 typologically diverse languages, generating over 1.4M SFT examples and training 240 student models. Our analyses reveal that model scale alone does not significantly predict teacher effectiveness: the most effective teachers we identify are consistently smaller than the largest models evaluated, and their ranking is stable across student base model families. Instead, data qualities such as prompt diversity, length, and response fluency capture 93.3% of the variance in intrinsic data quality and predict student performance. Finally, we provide practical recommendations, including matching the model families of teacher-student pairs and generating responses to existing prompts or translating them from English, which can yield improvements for less-resourced languages. We hope that our work advances data-centric research in multilingual synthetic data and LM development.

Lester James V. Miranda, Ivan Vulić, Anna Korhonen

Language Technology Lab, University of Cambridge

Supervised Fine-TuningMultilingual Language ModelsMultilingual Language Model EvaluationLanguage Model Generation EvaluationSynthetic Data GenerationSynthetic Data Generation for Language Models+1
AskPDF
Apr 10, 2026

Litmus (Re)Agent: A Benchmark and Agentic System for Predictive Evaluation of Multilingual Models

We study predictive multilingual evaluation: estimating how well a model will perform on a task in a target language when direct benchmark results are missing. This problem is common in multilingual deployment, where evaluation coverage is sparse and published evidence is uneven across languages, tasks, and model families. We introduce a controlled benchmark of 1,500 questions spanning six tasks and five evidence scenarios. The benchmark separates accessible evidence from ground truth, enabling evaluation of systems that must infer missing results from incomplete literature evidence. We also present Litmus (Re)Agent, a DAG-orchestrated agentic system that decomposes queries into hypotheses, retrieves evidence, and synthesises predictions through feature-aware aggregation. Across six systems, Litmus (Re)Agent achieves the best overall performance, with the largest gains in transfer-heavy scenarios where direct evidence is weak or absent. These results show that structured agentic reasoning is a promising approach to multilingual performance estimation under incomplete evidence.

Avni Mittal, Shanu Kumar, Sandipan Dandapat +1

Microsoft Corporation, India · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · Indian Institute of Technology Hyderabad

Multilingual Language Model EvaluationBenchmark DesignAgentic AI
AskPDF
Apr 8, 2026

Language Bias under Conflicting Information in Multilingual LLMs

Large Language Models (LLMs) have been shown to contain biases in the process of integrating conflicting information when answering questions. Here we ask whether such biases also exist with respect to which language is used for each conflicting piece of information. To answer this question, we extend the conflicting needles in a haystack paradigm to a multilingual setting and perform a comprehensive set of evaluations with naturalistic news domain data in five different languages, for a range of multilingual LLMs of different sizes. We find that all LLMs tested, including GPT-5.2, ignore the conflict and confidently assert only one of the possible answers in the large majority of cases. Furthermore, there is a consistent bias across models and prompting languages in which languages are preferred, with a general bias against Russian and, for the longest context lengths, in favor of Chinese. The language preferences are consistent between models trained inside and outside of mainland China, though somewhat stronger in the former category. There is also a general tendency among models to prioritize information that matches the language used for prompting. We hope to make users and developers of multilingual LLMs aware of this category of biases, to spur further research on their causes and possible mitigation.

Robert Östling, Murathan Kurfalı

Stockholm University Sweden · RISE Research Institutes of Sweden Sweden

Linguistic Bias in Language ModelsLanguage Model Bias EvaluationMultilingual Language ModelsKnowledge Conflicts in Language ModelsMultilingual Language Model Evaluation
AskPDF
Apr 8, 2026

To Adapt or not to Adapt, Rethinking the Value of Medical Knowledge-Aware Large Language Models

BACKGROUND: Recent studies have shown that domain-adapted large language models (LLMs) do not consistently outperform general-purpose counterparts on standard medical benchmarks, raising questions about the need for specialized clinical adaptation. METHODS: We systematically compare general and clinical LLMs on a diverse set of multiple choice clinical question answering tasks in English and Spanish. We introduce a perturbation based evaluation benchmark that probes model robustness, instruction following, and sensitivity to adversarial variations. Our evaluation includes, one-step and two-step question transformations, multi prompt testing and instruction guided assessment. We analyze a range of state-of-the-art clinical models and their general-purpose counterparts, focusing on Llama 3.1-based models. Additionally, we introduce Marmoka, a family of lightweight 8B-parameter clinical LLMs for English and Spanish, developed via continual domain-adaptive pretraining on medical corpora and instructions. RESULTS: The experiments show that clinical LLMs do not consistently outperform their general purpose counterparts on English clinical tasks, even under the proposed perturbation based benchmark. However, for the Spanish subsets the proposed Marmoka models obtain better results compared to Llama. CONCLUSIONS: Our results show that, under current short-form MCQA benchmarks, clinical LLMs offer only marginal and unstable improvements over general-purpose models in English, suggesting that existing evaluation frameworks may be insufficient to capture genuine medical expertise. We further find that both general and clinical models exhibit substantial limitations in instruction following and strict output formatting. Finally, we demonstrate that robust medical LLMs can be successfully developed for low-resource languages such as Spanish, as evidenced by the Marmoka models.

Ane G. Domingo-Aldama, Iker De La Iglesia, Maitane Urruela +2

Medical LLMsDomain Adaptation for LLMsClinical Language Model EvaluationMultilingual Language Model EvaluationLanguage Model RobustnessInstruction Following
AskPDF
Apr 8, 2026

Multilingual Cognitive Impairment Detection in the Era of Foundation Models

We evaluate cognitive impairment (CI) classification from transcripts of speech in English, Slovene, and Korean. We compare zero-shot large language models (LLMs) used as direct classifiers under three input settings -- transcript-only, linguistic-features-only, and combined -- with supervised tabular approaches trained under a leave-one-out protocol. The tabular models operate on engineered linguistic features, transcript embeddings, and early or late fusion of both modalities. Across languages, zero-shot LLMs provide competitive no-training baselines, but supervised tabular models generally perform better, particularly when engineered linguistic features are included and combined with embeddings. Few-shot experiments focusing on embeddings indicate that the value of limited supervision is language-dependent, with some languages benefiting substantially from additional labelled examples while others remain constrained without richer feature representations. Overall, the results suggest that, in small-data CI detection, structured linguistic signals and simple fusion-based classifiers remain strong and reliable signals.

Damar Hoogland, Boshko Koloski, Jaya Caporusso +5

Jožef Stefan Institute, Ljubljana, Slovenia · Jožef Stefan International Postgraduate School, Ljubljana, Slovenia · Institute of Synergetics and Psychotherapy Research, Paracelsus Medical University, Salzburg, Austria +2

Speech-Based Dementia DetectionClinical Language Model EvaluationText ClassificationFeature FusionMultilingual Language Model Evaluation
AskPDF
Apr 7, 2026

Swiss-Bench 003: Evaluating LLM Reliability and Adversarial Security for Swiss Regulatory Contexts

The deployment of large language models (LLMs) in Swiss financial and regulatory contexts demands empirical evidence of both production reliability and adversarial security, dimensions not jointly operationalized in existing Swiss-focused evaluation frameworks. This paper introduces Swiss-Bench 003 (SBP-003), extending the HAAS (Helvetic AI Assessment Score) from six to eight dimensions by adding D7 (Self-Graded Reliability Proxy) and D8 (Adversarial Security). I evaluate ten frontier models across 808 Swiss-specific items in four languages (German, French, Italian, English), comprising seven Swiss-adapted benchmarks (Swiss TruthfulQA, Swiss IFEval, Swiss SimpleQA, Swiss NIAH, Swiss PII-Scope, System Prompt Leakage, and Swiss German Comprehension) targeting FINMA Guidance 08/2024, the revised Federal Act on Data Protection (nDSG), and OWASP Top 10 for LLMs. Self-graded D7 scores (73-94%) exceed externally judged D8 security scores (20-61%) by a wide margin, though these dimensions use non-comparable scoring regimes. System prompt leakage resistance ranges from 24.8% to 88.2%, while PII extraction defense remains weak (14-42%) across all models. Qwen 3.5 Plus achieves the highest self-graded D7 score (94.4%), while GPT-oss 120B achieves the highest D8 score (60.7%) despite being the lowest-cost model evaluated. All evaluations are zero-shot under provider default settings; D7 is self-graded and does not constitute independently validated accuracy. I provide conceptual mapping tables relating benchmark dimensions to FINMA model validation requirements, nDSG data protection obligations, and OWASP LLM risk categories.

Fatih Uenal

Department of Computer Science, University of Colorado Boulder

LLM EvaluationLLM ReliabilityLanguage Model Safety EvaluationAdversarial Robustness of Language ModelsMultilingual Language Model EvaluationPrivacy Leakage in Language Models
AskPDF
Apr 6, 2026

Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation

While Large Language Models (LLMs) are increasingly adopted as automated judges for evaluating generated text, their outputs are often costly, and highly sensitive to prompt design, language, and aggregation strategies, severely, which limits reproducibility. To address these challenges, we propose OmniScore, a family of complementary, deterministic learned metrics developed using small size (<<1B) parameter models. OmniScore approximates LLM-judge behavior while preserving the low latency and consistency of traditional model-based scoring. We trained the models large-scale synthetic supervision (∼\sim564k instances, in 107 languages) and evaluated using 8,617 manually annotated instances. The OmniScore family supports reliable, multi-dimensional scores across a variety of settings, including reference-based, source-grounded, and hybrid evaluations. We evaluate these models across question answering (QA), translation, and summarization in 6 languages. Our results demonstrate that lightweight, deterministic learned metrics provide a highly practical and scalable alternative to frontier LLMs. Our models and datasets can be found at https://huggingface.co/collections/QCRI/omniscore

Firoj Alam, Gagan Bhatia, Sahinur Rahman Laskar +1

Qatar Computing Research Institute, HBKU, Qatar · †UPES, India

Language Model Generation EvaluationMultilingual Language Model EvaluationLLM-as-a-Judge
AskPDF
Apr 6, 2026

Chinese Language Is Not More Efficient Than English in Vibe Coding: A Preliminary Study on Token Cost and Problem-Solving Rate

A claim has been circulating on social media and practitioner forums that Chinese prompts are more token-efficient than English for LLM coding tasks, potentially reducing costs by up to 40%. This claim has influenced developers to consider switching to Chinese for ``vibe coding'' to save on API costs. In this paper, we conduct a rigorous empirical study using SWE-bench Lite, a benchmark of software engineering tasks, to evaluate whether this claim of Chinese token efficiency holds up to scrutiny. Our results reveal three key findings: First, the efficiency advantage of Chinese is not observed. Second, token cost varies by model architecture in ways that defy simple assumptions: while MiniMax-2.7 shows 1.28x higher token costs for Chinese, GLM-5 actually consumes fewer tokens with Chinese prompts. Third, and most importantly, we found that the success rate when prompting in Chinese is generally lower than in English across all models we tested. We also measure cost efficiency as expected cost per successful task -- jointly accounting for token consumption and task resolution rate. These findings should be interpreted as preliminary evidence rather than a definitive conclusion, given the limited number of models evaluated and the narrow set of benchmarks tested due to resource constraints; they indicate that language effects on token cost are model-dependent, and that practitioners should not expect cost savings or performance gains just by switching their prompt language to Chinese.

Simiao Ren, Xingyu Shen, Yuchen Zhou +3

Tsang · ∗,†Scam.ai

LLM Inference EfficiencyMultilingual Code GenerationMultilingual Language Model EvaluationCode Language Models
AskPDF