{"total":177,"rows":[{"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":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214,"area":null},{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152,"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":"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":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"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":"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":"2209.12226","title":"Re-contextualizing Fairness in NLP: The Case of India","created":"2022-09-25","cited_by_count":55,"area":null},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2109.02903","title":"IndicBART: A Pre-trained Model for Indic Natural Language Generation","created":"2021-09-07","cited_by_count":39,"area":null},{"id":"2211.11418","title":"L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages","created":"2022-11-21","cited_by_count":35,"area":null},{"id":"2403.20147","title":"IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context","created":"2024-03-29","cited_by_count":32,"area":null},{"id":"2212.10168","title":"Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2212.10180","title":"IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages","created":"2022-12-20","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":"2109.10534","title":"Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan Languages","created":"2021-09-22","cited_by_count":24,"area":null},{"id":"2204.12543","title":"Data Bootstrapping Approaches to Improve Low Resource Abusive Language Detection for Indic Languages","created":"2022-04-26","cited_by_count":23,"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":"2106.03958","title":"Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study","created":"2021-06-07","cited_by_count":19,"area":null},{"id":"2205.03018","title":"Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users","created":"2022-05-06","cited_by_count":19,"area":null},{"id":"2210.03479","title":"Hate Speech and Offensive Language Detection in Bengali","created":"2022-10-07","cited_by_count":19,"area":null},{"id":"2305.14463","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2310.11748","title":"BanglaAbuseMeme: A Dataset for Bengali Abusive Meme Classification","created":"2023-10-18","cited_by_count":18,"area":null},{"id":"2305.06586","title":"SemEval-2023 Task 2: Fine-grained Multilingual Named Entity Recognition (MultiCoNER 2)","created":"2023-05-11","cited_by_count":17,"area":null},{"id":"2503.19075","title":"The Case for \"Thick Evaluations\" of Cultural Representation in AI","created":"2025-03-24","cited_by_count":17,"area":null},{"id":"2304.11434","title":"L3Cube-IndicSBERT: A simple approach for learning cross-lingual sentence representations using multilingual BERT","created":"2023-04-22","cited_by_count":15,"area":null},{"id":"2106.02834","title":"MergeDistill: Merging Pre-trained Language Models using Distillation","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2106.03269","title":"Itihasa: A large-scale corpus for Sanskrit to English translation","created":"2021-06-06","cited_by_count":13,"area":null},{"id":"2305.15814","title":"Bhasha-Abhijnaanam: Native-script and romanized Language Identification for 22 Indic languages","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2204.13743","title":"HiNER: A Large Hindi Named Entity Recognition Dataset","created":"2022-04-28","cited_by_count":12,"area":null},{"id":"2211.11187","title":"L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi","created":"2022-11-21","cited_by_count":10,"area":null},{"id":"2307.05083","title":"Vacaspati: A Diverse Corpus of Bangla Literature","created":"2023-07-11","cited_by_count":10,"area":null},{"id":"2410.13281","title":"BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla","created":"2024-10-17","cited_by_count":10,"area":null},{"id":"2407.08790","title":"Large Models of What? Mistaking Engineering Achievements for Human Linguistic Agency","created":"2024-07-11","cited_by_count":9,"area":null},{"id":"2508.08424","title":"Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment","created":"2025-08-11","cited_by_count":9,"area":null},{"id":"2203.12524","title":"Computational historical linguistics and language diversity in South Asia","created":"2022-03-23","cited_by_count":8,"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":"2401.02254","title":"L3Cube-IndicNews: News-based Short Text and Long Document Classification Datasets in Indic Languages","created":"2024-01-04","cited_by_count":8,"area":null},{"id":"2310.16183","title":"BLP-2023 Task 2: Sentiment Analysis","created":"2023-10-24","cited_by_count":7,"area":null},{"id":"2310.18023","title":"SentMix-3L: A Bangla-English-Hindi Code-Mixed Dataset for Sentiment Analysis","created":"2023-10-27","cited_by_count":7,"area":null},{"id":"2403.18933","title":"SemEval-2024 Task 1: Semantic Textual Relatedness for African and Asian Languages","created":"2024-03-27","cited_by_count":7,"area":null},{"id":"2407.00416","title":"Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs","created":"2024-06-29","cited_by_count":7,"area":null},{"id":"2108.03886","title":"Do Images really do the Talking? Analysing the significance of Images in Tamil Troll meme classification","created":"2021-08-09","cited_by_count":6,"area":null},{"id":"2108.12177","title":"Offensive Language Identification in Low-resourced Code-mixed Dravidian languages using Pseudo-labeling","created":"2021-08-27","cited_by_count":6,"area":null},{"id":"2204.05814","title":"MuCoT: Multilingual Contrastive Training for Question-Answering in Low-resource Languages","created":"2022-04-12","cited_by_count":6,"area":null},{"id":"2207.03422","title":"AsNER -- Annotated Dataset and Baseline for Assamese Named Entity recognition","created":"2022-07-07","cited_by_count":6,"area":null},{"id":"2211.08547","title":"ALIGN-MLM: Word Embedding Alignment is Crucial for Multilingual Pre-training","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2306.13888","title":"L3Cube-MahaSent-MD: A Multi-domain Marathi Sentiment Analysis Dataset and Transformer Models","created":"2023-06-24","cited_by_count":6,"area":null},{"id":"2404.18216","title":"L3Cube-MahaNews: News-based Short Text and Long Document Classification Datasets in Marathi","created":"2024-04-28","cited_by_count":6,"area":null},{"id":"2406.03893","title":"How Good is Zero-Shot MT Evaluation for Low Resource Indian Languages?","created":"2024-06-06","cited_by_count":6,"area":null},{"id":"2410.21321","title":"User-Aware Multilingual Abusive Content Detection in Social Media","created":"2024-10-26","cited_by_count":6,"area":null},{"id":"2211.10163","title":"Overview of the HASOC Subtrack at FIRE 2022: Offensive Language Identification in Marathi","created":"2022-11-18","cited_by_count":5,"area":null},{"id":"2310.18387","title":"OffMix-3L: A Novel Code-Mixed Dataset in Bangla-English-Hindi for Offensive Language Identification","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2410.10407","title":"MMCFND: Multimodal Multilingual Caption-aware Fake News Detection for Low-resource Indic Languages","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2505.03688","title":"IndicSQuAD: A Comprehensive Multilingual Question Answering Dataset for Indic Languages","created":"2025-05-06","cited_by_count":5,"area":null},{"id":"2107.09931","title":"The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding","created":"2021-07-21","cited_by_count":4,"area":null},{"id":"2201.00598","title":"Toxicity Detection for Indic Multilingual Social Media Content","created":"2022-01-03","cited_by_count":4,"area":null},{"id":"2202.00291","title":"XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages","created":"2022-02-01","cited_by_count":4,"area":null},{"id":"2210.04267","title":"Spread Love Not Hate: Undermining the Importance of Hateful Pre-training for Hate Speech Detection","created":"2022-10-09","cited_by_count":4,"area":null},{"id":"2211.11206","title":"Cultural Re-contextualization of Fairness Research in Language Technologies in India","created":"2022-11-21","cited_by_count":4,"area":null},{"id":"2305.13641","title":"AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2309.10272","title":"Mixed-Distil-BERT: Code-mixed Language Modeling for Bangla, English, and Hindi","created":"2023-09-19","cited_by_count":4,"area":null},{"id":"2309.15779","title":"Question answering using deep learning in low resource Indian language Marathi","created":"2023-09-27","cited_by_count":4,"area":null},{"id":"2312.05671","title":"Hate Speech and Offensive Content Detection in Indo-Aryan Languages: A Battle of LSTM and Transformers","created":"2023-12-09","cited_by_count":4,"area":null},{"id":"2405.12929","title":"Code-mixed Sentiment and Hate-speech Prediction","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2406.17375","title":"An Empirical Study on the Characteristics of Bias upon Context Length Variation for Bangla","created":"2024-06-25","cited_by_count":4,"area":null},{"id":"2410.18390","title":"Monolingual and Multilingual Misinformation Detection for Low-Resource Languages: A Comprehensive Survey","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2505.23714","title":"SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2110.09393","title":"Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2209.03661","title":"Efficient Gender Debiasing of Pre-trained Indic Language Models","created":"2022-09-08","cited_by_count":3,"area":null},{"id":"2212.10039","title":"A Twitter BERT Approach for Offensive Language Detection in Marathi","created":"2022-12-20","cited_by_count":3,"area":null},{"id":"2302.14635","title":"H-AES: Towards Automated Essay Scoring for Hindi","created":"2023-02-28","cited_by_count":3,"area":null},{"id":"2306.06384","title":"Adversarial Training For Low-Resource Disfluency Correction","created":"2023-06-10","cited_by_count":3,"area":null},{"id":"2309.02915","title":"Persona-aware Generative Model for Code-mixed Language","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2311.15029","title":"nlpBDpatriots at BLP-2023 Task 1: A Two-Step Classification for Violence Inciting Text Detection in Bangla","created":"2023-11-25","cited_by_count":3,"area":null},{"id":"2401.14360","title":"A Comparative Analysis of Noise Reduction Methods in Sentiment Analysis on Noisy Bangla Texts","created":"2024-01-25","cited_by_count":3,"area":null},{"id":"2412.08163","title":"NLPineers@ NLU of Devanagari Script Languages 2025: Hate Speech Detection using Ensembling of BERT-based models","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2204.12587","title":"hate-alert@DravidianLangTech-ACL2022: Ensembling Multi-Modalities for Tamil TrollMeme Classification","created":"2022-03-25","cited_by_count":2,"area":null},{"id":"2204.12753","title":"A Comprehensive Understanding of Code-mixed Language Semantics using Hierarchical Transformer","created":"2022-04-27","cited_by_count":2,"area":null},{"id":"2205.06118","title":"Findings of the Shared Task on Offensive Span Identification from Code-Mixed Tamil-English Comments","created":"2022-05-12","cited_by_count":2,"area":null},{"id":"2212.07043","title":"AsPOS: Assamese Part of Speech Tagger using Deep Learning Approach","created":"2022-12-14","cited_by_count":2,"area":null},{"id":"2305.12518","title":"VAKTA-SETU: A Speech-to-Speech Machine Translation Service in Select Indic Languages","created":"2023-05-21","cited_by_count":2,"area":null},{"id":"2306.14030","title":"My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarks","created":"2023-06-24","cited_by_count":2,"area":null},{"id":"2310.02790","title":"Low Resource Summarization using Pre-trained Language Models","created":"2023-10-04","cited_by_count":2,"area":null},{"id":"2310.13080","title":"From Multilingual Complexity to Emotional Clarity: Leveraging Commonsense to Unveil Emotions in Code-Mixed Dialogues","created":"2023-10-19","cited_by_count":2,"area":null},{"id":"2311.12475","title":"PhayaThaiBERT: Enhancing a Pretrained Thai Language Model with Unassimilated Loanwords","created":"2023-11-21","cited_by_count":2,"area":null},{"id":"2311.15032","title":"nlpBDpatriots at BLP-2023 Task 2: A Transfer Learning Approach to Bangla Sentiment Analysis","created":"2023-11-25","cited_by_count":2,"area":null},{"id":"2312.01500","title":"Unsupervised Approach to Evaluate Sentence-Level Fluency: Do We Really Need Reference?","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2405.06922","title":"EmoMix-3L: A Code-Mixed Dataset for Bangla-English-Hindi Emotion Detection","created":"2024-05-11","cited_by_count":2,"area":null},{"id":"2405.20755","title":"Improving code-mixed hate detection by native sample mixing: A case study for Hindi-English code-mixed scenario","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2410.02611","title":"IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages?","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2412.12761","title":"Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2505.12587","title":"CMLFormer: A Dual Decoder Transformer with Switching Point Learning for Code-Mixed Language Modeling","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2110.02852","title":"Pretrained Transformers for Offensive Language Identification in Tanglish","created":"2021-10-06","cited_by_count":1,"area":null},{"id":"2110.12780","title":"Battling Hateful Content in Indic Languages HASOC '21","created":"2021-10-25","cited_by_count":1,"area":null},{"id":"2209.11252","title":"XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2210.14380","title":"Progressive Sentiment Analysis for Code-Switched Text Data","created":"2022-10-25","cited_by_count":1,"area":null}],"next_cursor":"100"}