{"total":120,"rows":[{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309,"area":"safety"},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151,"area":null},{"id":"2410.15553","title":"Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following","created":"2024-10-21","cited_by_count":102,"area":null},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94,"area":null},{"id":"2401.13136","title":"The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts","created":"2024-01-23","cited_by_count":94,"area":"alignment"},{"id":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","cited_by_count":72,"area":null},{"id":"2305.14857","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","created":"2023-05-24","cited_by_count":68,"area":null},{"id":"2411.14198","title":"Why do language models perform worse for morphologically complex languages?","created":"2024-11-21","cited_by_count":62,"area":null},{"id":"2210.08523","title":"Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP World","created":"2022-10-16","cited_by_count":55,"area":null},{"id":"2201.11732","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","created":"2022-01-27","cited_by_count":54,"area":null},{"id":"2212.08011","title":"Multi-VALUE: A Framework for Cross-Dialectal English NLP","created":"2022-12-15","cited_by_count":53,"area":null},{"id":"2501.17047","title":"How Linguistics Learned to Stop Worrying and Love the Language Models","created":"2025-01-28","cited_by_count":51,"area":null},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2505.24119","title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","created":"2025-05-30","cited_by_count":45,"area":"safety"},{"id":"2203.09435","title":"Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation","created":"2022-03-17","cited_by_count":44,"area":null},{"id":"2406.10118","title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages","created":"2024-06-14","cited_by_count":43,"area":null},{"id":"2404.11553","title":"Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages","created":"2024-04-17","cited_by_count":38,"area":null},{"id":"2408.06929","title":"Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas","created":"2024-08-13","cited_by_count":37,"area":null},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34,"area":null},{"id":"2206.03216","title":"Data Governance in the Age of Large-Scale Data-Driven Language Technology","created":"2022-05-04","cited_by_count":33,"area":null},{"id":"2310.15135","title":"Quantifying the Dialect Gap and its Correlates Across Languages","created":"2023-10-23","cited_by_count":33,"area":null},{"id":"2311.09205","title":"When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2407.12874","title":"SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning","created":"2024-07-16","cited_by_count":32,"area":null},{"id":"2410.15037","title":"mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation","created":"2024-10-19","cited_by_count":32,"area":null},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2210.14712","title":"Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks","created":"2022-10-26","cited_by_count":28,"area":null},{"id":"2211.15649","title":"Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2402.18120","title":"Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?","created":"2024-02-28","cited_by_count":24,"area":"alignment"},{"id":"2112.03497","title":"Dataset Geography: Mapping Language Data to Language Users","created":"2021-12-07","cited_by_count":22,"area":null},{"id":"2401.06408","title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters","created":"2024-01-12","cited_by_count":22,"area":null},{"id":"2204.05541","title":"Not always about you: Prioritizing community needs when developing endangered language technology","created":"2022-04-12","cited_by_count":21,"area":null},{"id":"2205.12676","title":"Evaluating the Diversity, Equity and Inclusion of NLP Technology: A Case Study for Indian Languages","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2204.11909","title":"How can NLP Help Revitalize Endangered Languages? A Case Study and Roadmap for the Cherokee Language","created":"2022-04-25","cited_by_count":19,"area":null},{"id":"2404.06138","title":"Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages","created":"2024-04-09","cited_by_count":18,"area":null},{"id":"2405.13777","title":"No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models","created":"2024-05-22","cited_by_count":16,"area":"mllm"},{"id":"2508.07414","title":"Grounding Multilingual Multimodal LLMs With Cultural Knowledge","created":"2025-08-10","cited_by_count":16,"area":"mllm"},{"id":"2404.19159","title":"What Drives Performance in Multilingual Language Models?","created":"2024-04-29","cited_by_count":15,"area":null},{"id":"2208.13078","title":"MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages","created":"2022-08-27","cited_by_count":13,"area":null},{"id":"2207.00758","title":"MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages","created":"2022-07-02","cited_by_count":11,"area":null},{"id":"2311.05746","title":"Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models","created":"2023-11-09","cited_by_count":11,"area":"mllm"},{"id":"2410.15263","title":"Back to School: Translation Using Grammar Books","created":"2024-10-20","cited_by_count":11,"area":null},{"id":"2301.08115","title":"Language Embeddings Sometimes Contain Typological Generalizations","created":"2023-01-19","cited_by_count":9,"area":null},{"id":"2305.14716","title":"GlobalBench: A Benchmark for Global Progress in Natural Language Processing","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2305.17202","title":"BIG-C: a Multimodal Multi-Purpose Dataset for Bemba","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2305.17267","title":"CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2305.19216","title":"Translation-Enhanced Multilingual Text-to-Image Generation","created":"2023-05-30","cited_by_count":9,"area":null},{"id":"2307.15493","title":"The timing bottleneck: Why timing and overlap are mission-critical for conversational user interfaces, speech recognition and dialogue systems","created":"2023-07-28","cited_by_count":9,"area":null},{"id":"2310.17769","title":"Social Contract AI: Aligning AI Assistants with Implicit Group Norms","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2202.12875","title":"DataLab: A Platform for Data Analysis and Intervention","created":"2022-02-25","cited_by_count":8,"area":null},{"id":"2305.06530","title":"How Good are Commercial Large Language Models on African Languages?","created":"2023-05-11","cited_by_count":8,"area":null},{"id":"2404.18534","title":"Evaluating and Mitigating Linguistic Discrimination in Large Language Models","created":"2024-04-29","cited_by_count":8,"area":"safety"},{"id":"2511.00657","title":"Do You Know About My Nation? Investigating Multilingual Language Models' Cultural Literacy Through Factual Knowledge","created":"2025-11-01","cited_by_count":8,"area":null},{"id":"2412.09415","title":"Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2508.19269","title":"Should LLMs be WEIRD? Exploring WEIRDness and Human Rights in Large Language Models","created":"2025-08-22","cited_by_count":7,"area":null},{"id":"2209.13515","title":"Assessing Digital Language Support on a Global Scale","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2305.14263","title":"LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2310.12794","title":"Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2406.14678","title":"Evaluating Contextualized Representations of (Spanish) Ambiguous Words: A New Lexical Resource and Empirical Analysis","created":"2024-06-20","cited_by_count":5,"area":null},{"id":"2406.17385","title":"Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2407.04459","title":"Generalists vs. Specialists: Evaluating Large Language Models for Urdu","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2503.24102","title":"Is Small Language Model the Silver Bullet to Low-Resource Languages Machine Translation?","created":"2025-03-31","cited_by_count":5,"area":null},{"id":"2509.15001","title":"BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings","created":"2025-09-18","cited_by_count":5,"area":null},{"id":"2203.10250","title":"Meta-X$_{NLG}$: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation","created":"2022-03-19","cited_by_count":4,"area":null},{"id":"2306.02349","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2310.08078","title":"To token or not to token: A Comparative Study of Text Representations for Cross-Lingual Transfer","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2310.12892","title":"A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2404.05365","title":"NLP Progress in Indigenous Latin American Languages","created":"2024-04-08","cited_by_count":4,"area":null},{"id":"2406.06021","title":"Shoulders of Giants: A Look at the Degree and Utility of Openness in NLP Research","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2505.20875","title":"Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2409.12746","title":"Bilingual Evaluation of Language Models on General Knowledge in University Entrance Exams with Minimal Contamination","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2602.12018","title":"Artificial intelligence is creating a new global linguistic hierarchy","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2203.09632","title":"Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages","created":"2022-03-17","cited_by_count":2,"area":null},{"id":"2211.05015","title":"Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2304.12979","title":"GMNLP at SemEval-2023 Task 12: Sentiment Analysis with Phylogeny-Based Adapters","created":"2023-04-25","cited_by_count":2,"area":null},{"id":"2305.15637","title":"Morphological Inflection: A Reality Check","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2412.16365","title":"Overview of the First Workshop on Language Models for Low-Resource Languages (LoResLM 2025)","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2503.11911","title":"LAG-MMLU: Benchmarking Frontier LLM Understanding in Latvian and Giriama","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2511.10664","title":"Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkish","created":"2025-11-05","cited_by_count":2,"area":null},{"id":"2602.16811","title":"Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmark","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2603.01211","title":"A Unified Framework to Quantify Cultural Intelligence of AI","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2210.16960","title":"Multilingual Multimodality: A Taxonomical Survey of Datasets, Techniques, Challenges and Opportunities","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2306.09752","title":"Politeness Stereotypes and Attack Vectors: Gender Stereotypes in Japanese and Korean Language Models","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2407.09861","title":"A Systematic Survey of Natural Language Processing for the Greek Language","created":"2024-07-13","cited_by_count":1,"area":null},{"id":"2507.18918","title":"Uncovering Cross-Linguistic Disparities in LLMs using Sparse Autoencoders","created":"2025-07-25","cited_by_count":1,"area":"mechinterp"},{"id":"2508.06435","title":"Learning the Topic, Not the Language: How LLMs Classify Online Immigration Discourse Across Languages","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2510.14307","title":"MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2512.17344","title":"Governance-Aware Hybrid Fine-Tuning for Multilingual Large Language Models","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2602.20065","title":"Multilingual Large Language Models do not comprehend all natural languages to equal degrees","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2605.26935","title":"DunbaaBERT: From Sacrifice to Semantics","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2608.03803","title":"M-GATE: Multilingual Grammar, Accuracy in Translation, and Efficiency Benchmark for Large Language Models","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2205.10411","title":"Educational Tools for Mapuzugun","created":"2022-05-19","cited_by_count":0,"area":null},{"id":"2305.03873","title":"Train Global, Tailor Local: Minimalist Multilingual Translation into Endangered Languages","created":"2023-05-05","cited_by_count":0,"area":null},{"id":"2309.00949","title":"Multilingual Text Representation","created":"2023-09-02","cited_by_count":0,"area":null},{"id":"2310.19687","title":"Sentiment Analysis in Digital Spaces: An Overview of Reviews","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2412.13924","title":"Language verY Rare for All","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2502.17945","title":"Assessing Agentic Large Language Models in Multilingual National Bias","created":"2025-02-25","cited_by_count":0,"area":"agents"},{"id":"2503.03582","title":"Scaling Crowdsourced Election Monitoring: Construction and Evaluation of Classification Models for Multilingual and Cross-Domain Classification Settings","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2505.13628","title":"Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2505.18159","title":"Advancing Uto-Aztecan Language Technologies: A Case Study on the Endangered Comanche Language","created":"2025-05-10","cited_by_count":0,"area":null}],"next_cursor":"100"}