{"total":201,"rows":[{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744,"area":null},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"id":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218,"area":null},{"id":"2304.05613","title":"ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning","created":"2023-04-12","cited_by_count":206,"area":null},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168,"area":null},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"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":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2212.05409","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","created":"2022-12-11","cited_by_count":102,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95,"area":null},{"id":"2205.10964","title":"The Geometry of Multilingual Language Model Representations","created":"2022-05-22","cited_by_count":95,"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":"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":"2106.06937","title":"Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning","created":"2021-06-13","cited_by_count":65,"area":null},{"id":"2109.12068","title":"AraT5: Text-to-Text Transformers for Arabic Language Generation","created":"2021-08-31","cited_by_count":63,"area":null},{"id":"2109.09138","title":"Multi-Task Learning in Natural Language Processing: An Overview","created":"2021-09-19","cited_by_count":62,"area":null},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57,"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":"2104.06387","title":"ExplainaBoard: An Explainable Leaderboard for NLP","created":"2021-04-13","cited_by_count":50,"area":null},{"id":"2104.08726","title":"AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages","created":"2021-04-18","cited_by_count":50,"area":null},{"id":"2403.11009","title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages","created":"2024-03-16","cited_by_count":50,"area":null},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2106.16171","title":"Revisiting the Primacy of English in Zero-shot Cross-lingual Transfer","created":"2021-06-30","cited_by_count":47,"area":null},{"id":"2212.10758","title":"ORCA: A Challenging Benchmark for Arabic Language Understanding","created":"2022-12-21","cited_by_count":47,"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":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"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":"2212.09660","title":"The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges","created":"2022-12-19","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":"2105.00827","title":"AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2104.08006","title":"ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation","created":"2021-04-16","cited_by_count":31,"area":null},{"id":"2110.05877","title":"OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages","created":"2021-10-12","cited_by_count":31,"area":null},{"id":"2503.05500","title":"EuroBERT: Scaling Multilingual Encoders for European Languages","created":"2025-03-07","cited_by_count":31,"area":null},{"id":"2205.10400","title":"Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog","created":"2022-05-20","cited_by_count":30,"area":null},{"id":"2206.02291","title":"Pretrained Models for Multilingual Federated Learning","created":"2022-06-06","cited_by_count":30,"area":null},{"id":"2104.05433","title":"Multilingual Language Models Predict Human Reading Behavior","created":"2021-04-12","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":"2301.13720","title":"Zero-shot cross-lingual transfer language selection using linguistic similarity","created":"2023-01-31","cited_by_count":28,"area":null},{"id":"2305.15678","title":"Revisiting non-English Text Simplification: A Unified Multilingual Benchmark","created":"2023-05-25","cited_by_count":27,"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":"2204.08776","title":"IndicXNLI: Evaluating Multilingual Inference for Indian Languages","created":"2022-04-19","cited_by_count":26,"area":null},{"id":"2203.01976","title":"Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages","created":"2022-03-03","cited_by_count":25,"area":null},{"id":"2103.09593","title":"Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots","created":"2021-03-17","cited_by_count":23,"area":null},{"id":"2305.08414","title":"What's the Meaning of Superhuman Performance in Today's NLU?","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2108.07140","title":"MTG: A Benchmark Suite for Multilingual Text Generation","created":"2021-08-13","cited_by_count":22,"area":null},{"id":"2112.11031","title":"On Cross-Lingual Retrieval with Multilingual Text Encoders","created":"2021-12-21","cited_by_count":22,"area":null},{"id":"2104.08645","title":"Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training","created":"2021-04-17","cited_by_count":21,"area":null},{"id":"2104.07554","title":"Zero-Shot Cross-lingual Semantic Parsing","created":"2021-04-15","cited_by_count":19,"area":null},{"id":"2109.12573","title":"XLM-K: Improving Cross-Lingual Language Model Pre-training with Multilingual Knowledge","created":"2021-09-26","cited_by_count":18,"area":null},{"id":"2104.08570","title":"Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems","created":"2021-04-17","cited_by_count":17,"area":null},{"id":"2504.21099","title":"A Survey on Parameter-Efficient Fine-Tuning for Foundation Models in Federated Learning","created":"2025-04-29","cited_by_count":17,"area":null},{"id":"2101.08370","title":"Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval","created":"2021-01-21","cited_by_count":16,"area":null},{"id":"2106.09889","title":"GEM: A General Evaluation Benchmark for Multimodal Tasks","created":"2021-06-18","cited_by_count":16,"area":null},{"id":"2210.12360","title":"Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models","created":"2022-10-22","cited_by_count":16,"area":null},{"id":"2304.00906","title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","created":"2023-04-03","cited_by_count":16,"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":"2503.14603","title":"Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2210.05769","title":"Vote'n'Rank: Revision of Benchmarking with Social Choice Theory","created":"2022-10-11","cited_by_count":15,"area":null},{"id":"2305.12199","title":"VNHSGE: VietNamese High School Graduation Examination Dataset for Large Language Models","created":"2023-05-20","cited_by_count":15,"area":null},{"id":"2401.01053","title":"Cheetah: Natural Language Generation for 517 African Languages","created":"2024-01-02","cited_by_count":15,"area":null},{"id":"2203.03047","title":"Recent Advances in Neural Text Generation: A Task-Agnostic Survey","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2208.04826","title":"Compositional Evaluation on Japanese Textual Entailment and Similarity","created":"2022-08-09","cited_by_count":14,"area":null},{"id":"2311.09033","title":"MELA: Multilingual Evaluation of Linguistic Acceptability","created":"2023-11-15","cited_by_count":14,"area":null},{"id":"2111.10962","title":"Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triples","created":"2021-11-22","cited_by_count":13,"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":"2211.13112","title":"This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish","created":"2022-11-23","cited_by_count":13,"area":null},{"id":"2504.09714","title":"Evaluating the Quality of Benchmark Datasets for Low-Resource Languages: A Case Study on Turkish","created":"2025-04-13","cited_by_count":13,"area":null},{"id":"2105.11246","title":"Cross-lingual Text Classification with Heterogeneous Graph Neural Network","created":"2021-05-24","cited_by_count":12,"area":null},{"id":"2106.04832","title":"Probing Multilingual Language Models for Discourse","created":"2021-06-09","cited_by_count":12,"area":null},{"id":"2205.15051","title":"X-SCITLDR: Cross-Lingual Extreme Summarization of Scholarly Documents","created":"2022-05-30","cited_by_count":12,"area":null},{"id":"2412.00532","title":"ChemTEB: Chemical Text Embedding Benchmark, an Overview of Embedding Models Performance & Efficiency on a Specific Domain","created":"2024-11-30","cited_by_count":12,"area":null},{"id":"2105.02472","title":"XeroAlign: Zero-Shot Cross-lingual Transformer Alignment","created":"2021-05-06","cited_by_count":11,"area":null},{"id":"2106.02134","title":"Syntax-augmented Multilingual BERT for Cross-lingual Transfer","created":"2021-06-03","cited_by_count":11,"area":null},{"id":"2209.12577","title":"Meta-Learning a Cross-lingual Manifold for Semantic Parsing","created":"2022-09-26","cited_by_count":11,"area":null},{"id":"2211.09722","title":"Federated Multilingual Models for Medical Transcript Analysis","created":"2022-11-04","cited_by_count":11,"area":null},{"id":"2104.09696","title":"X-METRA-ADA: Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding and Question Answering","created":"2021-04-20","cited_by_count":10,"area":null},{"id":"2112.04735","title":"From Good to Best: Two-Stage Training for Cross-lingual Machine Reading Comprehension","created":"2021-12-09","cited_by_count":10,"area":null},{"id":"2205.06356","title":"Beyond Static Models and Test Sets: Benchmarking the Potential of Pre-trained Models Across Tasks and Languages","created":"2022-05-12","cited_by_count":10,"area":null},{"id":"2307.08074","title":"Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling","created":"2023-07-16","cited_by_count":10,"area":null},{"id":"2402.17467","title":"Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2403.03909","title":"A Measure for Transparent Comparison of Linguistic Diversity in Multilingual NLP Data Sets","created":"2024-03-06","cited_by_count":10,"area":null},{"id":"2404.16766","title":"Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2501.15747","title":"IndicMMLU-Pro: Benchmarking Indic Large Language Models on Multi-Task Language Understanding","created":"2025-01-27","cited_by_count":10,"area":null},{"id":"2502.19582","title":"Where Are We? Evaluating LLM Performance on African Languages","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2106.02017","title":"A Dataset and Baselines for Multilingual Reply Suggestion","created":"2021-06-03","cited_by_count":9,"area":null},{"id":"2108.03509","title":"Compositional Generalization in Multilingual Semantic Parsing over Wikidata","created":"2021-08-07","cited_by_count":9,"area":null},{"id":"2112.01342","title":"How not to Lie with a Benchmark: Rearranging NLP Leaderboards","created":"2021-12-02","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":"2411.11171","title":"LL\\\"aMmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch","created":"2024-11-17","cited_by_count":9,"area":null},{"id":"2205.11159","title":"RuNNE-2022 Shared Task: Recognizing Nested Named Entities","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2206.00962","title":"Transfer Language Selection for Zero-Shot Cross-Lingual Abusive Language Detection","created":"2022-06-02","cited_by_count":8,"area":null},{"id":"2306.04996","title":"T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification","created":"2023-06-08","cited_by_count":8,"area":null},{"id":"2403.15882","title":"VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding","created":"2024-03-23","cited_by_count":8,"area":null},{"id":"2411.00311","title":"C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning","created":"2024-11-01","cited_by_count":8,"area":null},{"id":"2508.16431","title":"Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish","created":"2025-08-22","cited_by_count":8,"area":null},{"id":"2110.08975","title":"Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research","created":"2021-10-18","cited_by_count":7,"area":null}],"next_cursor":"100"}