{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"2310.16944","title":"Zephyr: Direct Distillation of LM Alignment","created":"2023-10-25","cited_by_count":506},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311},{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214},{"id":"2412.03304","title":"Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation","created":"2024-12-04","cited_by_count":191},{"id":"2010.12309","title":"A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios","created":"2020-10-23","cited_by_count":171},{"id":"2305.16307","title":"IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages","created":"2023-05-25","cited_by_count":152},{"id":"2104.05596","title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","created":"2021-04-12","cited_by_count":136},{"id":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109},{"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},{"id":"2503.10497","title":"MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation","created":"2025-03-13","cited_by_count":79},{"id":"2403.16512","title":"LLMs Are Few-Shot In-Context Low-Resource Language Learners","created":"2024-03-25","cited_by_count":68},{"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},{"id":"2209.12226","title":"Re-contextualizing Fairness in NLP: The Case of India","created":"2022-09-25","cited_by_count":55},{"id":"2403.06350","title":"IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages","created":"2024-03-11","cited_by_count":52},{"id":"2202.01159","title":"L3Cube-MahaCorpus and MahaBERT: Marathi Monolingual Corpus, Marathi BERT Language Models, and Resources","created":"2022-02-02","cited_by_count":51},{"id":"2406.01771","title":"LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback","created":"2024-06-03","cited_by_count":51},{"id":"2203.08351","title":"Towards Afrocentric NLP for African Languages: Where We Are and Where We Can Go","created":"2022-03-16","cited_by_count":47},{"id":"2203.05437","title":"IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages","created":"2022-03-10","cited_by_count":42},{"id":"2502.09457","title":"A Survey of Multilingual Reasoning in Language Models","created":"2025-02-13","cited_by_count":33},{"id":"2307.01503","title":"On Evaluating and Mitigating Gender Biases in Multilingual Settings","created":"2023-07-04","cited_by_count":31},{"id":"2406.17761","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","created":"2024-06-25","cited_by_count":31},{"id":"2401.14280","title":"RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization","created":"2024-01-25","cited_by_count":29},{"id":"2411.02538","title":"MILU: A Multi-task Indic Language Understanding Benchmark","created":"2024-11-04","cited_by_count":27},{"id":"2203.01976","title":"Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages","created":"2022-03-03","cited_by_count":25},{"id":"2407.13522","title":"INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages","created":"2024-07-18","cited_by_count":24},{"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},{"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},{"id":"2401.01596","title":"MedSumm: A Multimodal Approach to Summarizing Code-Mixed Hindi-English Clinical Queries","created":"2024-01-03","cited_by_count":19},{"id":"2310.06458","title":"Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features","created":"2023-10-10","cited_by_count":18},{"id":"2402.18045","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","created":"2024-02-28","cited_by_count":18},{"id":"2407.02118","title":"Breaking Language Barriers: Cross-Lingual Continual Pre-Training at Scale","created":"2024-07-02","cited_by_count":15},{"id":"2411.18571","title":"Challenges in Adapting Multilingual LLMs to Low-Resource Languages using LoRA PEFT Tuning","created":"2024-11-27","cited_by_count":14},{"id":"2008.04860","title":"Revisiting Low Resource Status of Indian Languages in Machine Translation","created":"2020-08-11","cited_by_count":12},{"id":"2212.04960","title":"BigScience: A Case Study in the Social Construction of a Multilingual Large Language Model","created":"2022-12-09","cited_by_count":11},{"id":"2305.08828","title":"PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India","created":"2023-05-15","cited_by_count":11},{"id":"2307.05083","title":"Vacaspati: A Diverse Corpus of Bangla Literature","created":"2023-07-11","cited_by_count":10},{"id":"2408.08964","title":"BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis","created":"2024-08-16","cited_by_count":10},{"id":"2305.17267","title":"CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation","created":"2023-05-26","cited_by_count":9},{"id":"2203.12524","title":"Computational historical linguistics and language diversity in South Asia","created":"2022-03-23","cited_by_count":8},{"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},{"id":"2504.14786","title":"Cultivating Multidisciplinary AI Workforce Development on iTiger GPU Cluster: Practices and Challenges","created":"2025-04-21","cited_by_count":8},{"id":"2403.05434","title":"Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs","created":"2024-03-08","cited_by_count":7},{"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},{"id":"2410.03576","title":"Table Question Answering for Low-resourced Indic Languages","created":"2024-10-04","cited_by_count":7},{"id":"2410.19517","title":"Detection of Human and Machine-Authored Fake News in Urdu","created":"2024-10-25","cited_by_count":7},{"id":"2502.04718","title":"Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics?","created":"2025-02-07","cited_by_count":7},{"id":"2408.02237","title":"Do Large Language Models Speak All Languages Equally? A Comparative Study in Low-Resource Settings","created":"2024-08-05","cited_by_count":6},{"id":"2410.15308","title":"LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content","created":"2024-10-20","cited_by_count":6},{"id":"2312.09508","title":"IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languages","created":"2023-12-15","cited_by_count":5},{"id":"2402.07262","title":"Low-Resource Counterspeech Generation for Indic Languages: The Case of Bengali and Hindi","created":"2024-02-11","cited_by_count":5},{"id":"2407.04459","title":"Generalists vs. Specialists: Evaluating Large Language Models for Urdu","created":"2024-07-05","cited_by_count":5},{"id":"2412.13860","title":"Domain-adaptative Continual Learning for Low-resource Tasks: Evaluation on Nepali","created":"2024-12-18","cited_by_count":5},{"id":"2004.10270","title":"Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi","created":"2020-04-21","cited_by_count":4},{"id":"2305.13641","title":"AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese","created":"2023-05-23","cited_by_count":4},{"id":"2309.10272","title":"Mixed-Distil-BERT: Code-mixed Language Modeling for Bangla, English, and Hindi","created":"2023-09-19","cited_by_count":4},{"id":"2401.13085","title":"IndiText Boost: Text Augmentation for Low Resource India Languages","created":"2024-01-23","cited_by_count":4},{"id":"2403.19142","title":"A Tulu Resource for Machine Translation","created":"2024-03-28","cited_by_count":4},{"id":"2503.04797","title":"Parallel Corpora for Machine Translation in Low-resource Indic Languages: A Comprehensive Review","created":"2025-03-02","cited_by_count":4},{"id":"2501.05749","title":"Bridging Dialects: Translating Standard Bangla to Regional Variants Using Neural Models","created":"2025-01-10","cited_by_count":3},{"id":"2312.02125","title":"TPPoet: Transformer-Based Persian Poem Generation using Minimal Data and Advanced Decoding Techniques","created":"2023-12-04","cited_by_count":2},{"id":"2402.13571","title":"Multilingual Coreference Resolution in Low-resource South Asian Languages","created":"2024-02-21","cited_by_count":2},{"id":"2409.05401","title":"Benchmarking and Building Zero-Shot Hindi Retrieval Model with Hindi-BEIR and NLLB-E5","created":"2024-09-09","cited_by_count":2},{"id":"2504.12553","title":"ELAB: Extensive LLM Alignment Benchmark in Persian Language","created":"2025-04-17","cited_by_count":2},{"id":"2311.07804","title":"IruMozhi: Automatically classifying diglossia in Tamil","created":"2023-11-13","cited_by_count":1},{"id":"2405.00717","title":"Exploring News Summarization and Enrichment in a Highly Resource-Scarce Indian Language: A Case Study of Mizo","created":"2024-04-25","cited_by_count":1},{"id":"2504.09753","title":"Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance","created":"2025-04-13","cited_by_count":1},{"id":"2507.13238","title":"Multilingual LLMs Are Not Multilingual Thinkers: Evidence from Hindi Analogy Evaluation","created":"2025-07-17","cited_by_count":1}],"next_cursor":null}