{"total":235,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2402.10588","title":"Do Llamas Work in English? On the Latent Language of Multilingual Transformers","created":"2024-02-16","cited_by_count":281,"area":null},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214,"area":null},{"id":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192,"area":null},{"id":"2309.04662","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","created":"2023-09-09","cited_by_count":181,"area":null},{"id":"2402.10811","title":"Quantifying the Persona Effect in LLM Simulations","created":"2024-02-16","cited_by_count":169,"area":null},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128,"area":null},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123,"area":null},{"id":"2404.17790","title":"Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities","created":"2024-04-27","cited_by_count":111,"area":null},{"id":"2306.05179","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models","created":"2023-06-08","cited_by_count":110,"area":null},{"id":"2312.00738","title":"SeaLLMs -- Large Language Models for Southeast Asia","created":"2023-12-01","cited_by_count":104,"area":null},{"id":"2309.04766","title":"SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning","created":"2023-09-09","cited_by_count":94,"area":null},{"id":"2309.07462","title":"Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?","created":"2023-09-14","cited_by_count":88,"area":null},{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2310.14542","title":"Evaluating Large Language Models on Controlled Generation Tasks","created":"2023-10-23","cited_by_count":73,"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":"2403.06412","title":"CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean","created":"2024-03-11","cited_by_count":66,"area":null},{"id":"2307.06018","title":"PolyLM: An Open Source Polyglot Large Language Model","created":"2023-07-12","cited_by_count":64,"area":null},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57,"area":null},{"id":"2404.16816","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","created":"2024-04-25","cited_by_count":56,"area":null},{"id":"2402.10946","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","created":"2024-02-09","cited_by_count":50,"area":null},{"id":"2409.11404","title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","created":"2024-09-17","cited_by_count":46,"area":null},{"id":"2311.07978","title":"AfroBench: How Good are Large Language Models on African Languages?","created":"2023-11-14","cited_by_count":43,"area":null},{"id":"2406.03368","title":"IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models","created":"2024-06-05","cited_by_count":43,"area":null},{"id":"2408.12547","title":"Towards Evaluating and Building Versatile Large Language Models for Medicine","created":"2024-08-22","cited_by_count":40,"area":null},{"id":"2311.08711","title":"PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning","created":"2023-11-15","cited_by_count":39,"area":null},{"id":"2405.11029","title":"Generative Artificial Intelligence: A Systematic Review and Applications","created":"2024-05-17","cited_by_count":37,"area":null},{"id":"2406.15053","title":"PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data","created":"2024-06-21","cited_by_count":37,"area":null},{"id":"2407.19672","title":"SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages","created":"2024-07-29","cited_by_count":36,"area":null},{"id":"2406.07243","title":"MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs","created":"2024-06-11","cited_by_count":35,"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":"2404.06228","title":"Understanding Cross-Lingual Alignment -- A Survey","created":"2024-04-09","cited_by_count":34,"area":null},{"id":"2305.14610","title":"This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models","created":"2023-05-24","cited_by_count":32,"area":null},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2401.15006","title":"Airavata: Introducing Hindi Instruction-tuned LLM","created":"2024-01-26","cited_by_count":32,"area":null},{"id":"2403.10258","title":"Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models","created":"2024-03-15","cited_by_count":31,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2312.13951","title":"Typhoon: Thai Large Language Models","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2402.19167","title":"Teaching Large Language Models an Unseen Language on the Fly","created":"2024-02-29","cited_by_count":30,"area":null},{"id":"2407.09823","title":"NativQA: Multilingual Culturally-Aligned Natural Query for LLMs","created":"2024-07-13","cited_by_count":30,"area":null},{"id":"2505.12201","title":"How Reliable is Multilingual LLM-as-a-Judge?","created":"2025-05-18","cited_by_count":30,"area":null},{"id":"2401.14280","title":"RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization","created":"2024-01-25","cited_by_count":29,"area":null},{"id":"2411.09116","title":"P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs","created":"2024-11-14","cited_by_count":29,"area":null},{"id":"2401.13303","title":"MaLA-500: Massive Language Adaptation of Large Language Models","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2403.03814","title":"Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ","created":"2024-03-06","cited_by_count":27,"area":null},{"id":"2404.04659","title":"Multilingual Pretraining and Instruction Tuning Improve Cross-Lingual Knowledge Alignment, But Only Shallowly","created":"2024-04-06","cited_by_count":27,"area":null},{"id":"2303.17003","title":"Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams","created":"2023-03-29","cited_by_count":25,"area":null},{"id":"2410.05873","title":"MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment","created":"2024-10-08","cited_by_count":25,"area":null},{"id":"2401.14362","title":"The Typing Cure: Experiences with Large Language Model Chatbots for Mental Health Support","created":"2024-01-25","cited_by_count":24,"area":null},{"id":"2403.00393","title":"TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMs","created":"2024-03-01","cited_by_count":24,"area":null},{"id":"2406.07302","title":"BertaQA: How Much Do Language Models Know About Local Culture?","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2404.07851","title":"Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations","created":"2024-04-11","cited_by_count":22,"area":null},{"id":"2502.09331","title":"Beyond English: The Impact of Prompt Translation Strategies across Languages and Tasks in Multilingual LLMs","created":"2025-02-13","cited_by_count":22,"area":null},{"id":"2402.17478","title":"Can GPT-4 Identify Propaganda? Annotation and Detection of Propaganda Spans in News Articles","created":"2024-02-27","cited_by_count":21,"area":null},{"id":"2404.00750","title":"Can Language Models Recognize Convincing Arguments?","created":"2024-03-31","cited_by_count":21,"area":null},{"id":"2308.04945","title":"LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking","created":"2023-08-09","cited_by_count":20,"area":null},{"id":"2308.10783","title":"Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis","created":"2023-08-21","cited_by_count":20,"area":null},{"id":"2311.09812","title":"Large Language Models for Propaganda Span Annotation","created":"2023-11-16","cited_by_count":19,"area":null},{"id":"2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","created":"2023-09-12","cited_by_count":18,"area":null},{"id":"2402.10496","title":"Comparing Hallucination Detection Metrics for Multilingual Generation","created":"2024-02-16","cited_by_count":18,"area":null},{"id":"2402.10712","title":"An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference","created":"2024-02-16","cited_by_count":18,"area":null},{"id":"2402.18045","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","created":"2024-02-28","cited_by_count":18,"area":null},{"id":"2404.01856","title":"Poro 34B and the Blessing of Multilinguality","created":"2024-04-02","cited_by_count":18,"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":"2305.14982","title":"LAraBench: Benchmarking Arabic AI with Large Language Models","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2307.14712","title":"Evaluating Generative Models for Graph-to-Text Generation","created":"2023-07-27","cited_by_count":16,"area":null},{"id":"2310.20470","title":"Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation","created":"2023-10-31","cited_by_count":16,"area":null},{"id":"2410.23825","title":"GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages","created":"2024-10-31","cited_by_count":16,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2305.13582","title":"Translation and Fusion Improves Zero-shot Cross-lingual Information Extraction","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2404.01667","title":"METAL: Towards Multilingual Meta-Evaluation","created":"2024-04-02","cited_by_count":15,"area":null},{"id":"2404.19159","title":"What Drives Performance in Multilingual Language Models?","created":"2024-04-29","cited_by_count":15,"area":null},{"id":"2406.15948","title":"Teaching LLMs to Abstain across Languages via Multilingual Feedback","created":"2024-06-22","cited_by_count":14,"area":null},{"id":"2410.13153","title":"Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2503.10688","title":"CULEMO: Cultural Lenses on Emotion -- Benchmarking LLMs for Cross-Cultural Emotion Understanding","created":"2025-03-12","cited_by_count":14,"area":null},{"id":"2402.12976","title":"The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis","created":"2024-02-20","cited_by_count":13,"area":null},{"id":"2409.08916","title":"Farmer.Chat: Scaling AI-Powered Agricultural Services for Smallholder Farmers","created":"2024-09-13","cited_by_count":13,"area":null},{"id":"2502.06298","title":"SeaExam and SeaBench: Benchmarking LLMs with Local Multilingual Questions in Southeast Asia","created":"2025-02-10","cited_by_count":13,"area":null},{"id":"2402.18025","title":"Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions","created":"2024-02-28","cited_by_count":12,"area":null},{"id":"2403.04792","title":"Breaking the Language Barrier: Can Direct Inference Outperform Pre-Translation in Multilingual LLM Applications?","created":"2024-03-04","cited_by_count":12,"area":null},{"id":"2411.05060","title":"A Guide to Misinformation Detection Data and Evaluation","created":"2024-11-07","cited_by_count":10,"area":null},{"id":"2502.15392","title":"Chitrarth: Bridging Vision and Language for a Billion People","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2504.06011","title":"Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2505.21548","title":"Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2309.08943","title":"Contextual Label Projection for Cross-Lingual Structured Prediction","created":"2023-09-16","cited_by_count":9,"area":null},{"id":"2402.04620","title":"CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract Patients","created":"2024-02-07","cited_by_count":9,"area":null},{"id":"2403.00794","title":"Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models","created":"2024-02-23","cited_by_count":9,"area":null},{"id":"2406.03776","title":"XL-HeadTags: Leveraging Multimodal Retrieval Augmentation for the Multilingual Generation of News Headlines and Tags","created":"2024-06-06","cited_by_count":9,"area":null},{"id":"2409.07054","title":"Native vs Non-Native Language Prompting: A Comparative Analysis","created":"2024-09-11","cited_by_count":9,"area":null},{"id":"2502.11187","title":"TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking","created":"2025-02-16","cited_by_count":9,"area":null},{"id":"2504.17720","title":"Multilingual Performance Biases of Large Language Models in Education","created":"2025-04-24","cited_by_count":9,"area":null},{"id":"2507.14900","title":"From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment","created":"2025-07-20","cited_by_count":9,"area":null},{"id":"2508.09115","title":"SinLlama -- A Large Language Model for Sinhala","created":"2025-08-12","cited_by_count":9,"area":null},{"id":"2305.17740","title":"Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs","created":"2023-05-28","cited_by_count":8,"area":null},{"id":"2405.05572","title":"From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2405.15453","title":"Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks","created":"2024-05-24","cited_by_count":8,"area":null}],"next_cursor":"100"}