{"total":95,"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":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"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":"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":"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":"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,"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":"2401.15006","title":"Airavata: Introducing Hindi Instruction-tuned LLM","created":"2024-01-26","cited_by_count":32,"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":"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":"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":"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":"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,"area":null},{"id":"2406.14670","title":"Exploring Design Choices for Building Language-Specific LLMs","created":"2024-06-20","cited_by_count":22,"area":null},{"id":"2407.05841","title":"An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models","created":"2024-07-08","cited_by_count":20,"area":null},{"id":"2407.03994","title":"Unlocking the Potential of Model Merging for Low-Resource Languages","created":"2024-07-04","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":"2410.13394","title":"Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs","created":"2024-10-17","cited_by_count":18,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2405.06346","title":"Akal Badi ya Bias: An Exploratory Study of Gender Bias in Hindi Language Technology","created":"2024-05-10","cited_by_count":17,"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":"2509.19274","title":"DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture","created":"2025-09-23","cited_by_count":13,"area":null},{"id":"2504.16977","title":"Tokenization Matters: Improving Zero-Shot NER for Indic Languages","created":"2025-04-23","cited_by_count":12,"area":null},{"id":"2312.07751","title":"Large Human Language Models: A Need and the Challenges","created":"2023-11-09","cited_by_count":11,"area":null},{"id":"2409.08706","title":"L3Cube-IndicQuest: A Benchmark Question Answering Dataset for Evaluating Knowledge of LLMs in Indic Context","created":"2024-09-13","cited_by_count":10,"area":null},{"id":"2502.09642","title":"Krutrim LLM: Multilingual Foundational Model for over a Billion People","created":"2025-02-10","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":"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":"2305.07491","title":"A Comprehensive Analysis of Adapter Efficiency","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2403.05434","title":"Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs","created":"2024-03-08","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":"2508.17162","title":"Quantifying Language Disparities in Multilingual Large Language Models","created":"2025-08-23","cited_by_count":7,"area":null},{"id":"2310.09141","title":"PuoBERTa: Training and evaluation of a curated language model for Setswana","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2403.13638","title":"Pretraining Language Models Using Translationese","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2411.15734","title":"Development of Pre-Trained Transformer-based Models for the Nepali Language","created":"2024-11-24","cited_by_count":6,"area":null},{"id":"2509.11570","title":"Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challenges","created":"2025-09-15","cited_by_count":6,"area":null},{"id":"2407.02317","title":"Soft Language Prompts for Language Transfer","created":"2024-07-02","cited_by_count":5,"area":null},{"id":"2502.14911","title":"Batayan: A Filipino NLP benchmark for evaluating Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2311.08348","title":"MC$^2$: Towards Transparent and Culturally-Aware NLP for Minority Languages in China","created":"2023-11-14","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":"2406.09559","title":"Decoding the Diversity: A Review of the Indic AI Research Landscape","created":"2024-06-13","cited_by_count":4,"area":null},{"id":"2505.18638","title":"Multilingual Question Answering in Low-Resource Settings: A Dzongkha-English Benchmark for Foundation Models","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2511.03237","title":"MUTANT: A Recipe for Multilingual Tokenizer Design","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2408.09437","title":"Hindi-BEIR : A Large Scale Retrieval Benchmark in Hindi","created":"2024-08-18","cited_by_count":3,"area":null},{"id":"2409.15380","title":"Kalahi: A handcrafted, grassroots cultural LLM evaluation suite for Filipino","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2508.16185","title":"ParamBench: A Graduate-Level Benchmark for Evaluating LLM Understanding on Indic Subjects","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2510.07000","title":"Pragyaan: Designing and Curating High-Quality Cultural Post-Training Datasets for Indian Languages","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2512.00333","title":"IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languages","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2604.24470","title":"Zero-shot Large Language Models for Automatic Readability Assessment","created":"2026-04-27","cited_by_count":3,"area":null},{"id":"2310.13228","title":"The Less the Merrier? Investigating Language Representation in Multilingual Models","created":"2023-10-20","cited_by_count":2,"area":null},{"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,"area":null},{"id":"2410.17901","title":"ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigrams","created":"2024-10-23","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":"2506.03793","title":"Mark My Words: A Robust Multilingual Model for Punctuation in Text and Speech Transcripts","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2508.19831","title":"Benchmarking Hindi LLMs: A New Suite of Datasets and a Comparative Analysis","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2512.01077","title":"ELR-1000: A Community-Generated Dataset for Endangered Indic Indigenous Languages","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2605.29379","title":"BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2402.15967","title":"Direct Punjabi to English speech translation using discrete units","created":"2024-02-25","cited_by_count":1,"area":null},{"id":"2501.16581","title":"DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2511.00486","title":"Leveraging the Cross-Domain & Cross-Linguistic Corpus for Low Resource NMT: A Case Study On Bhili-Hindi-English Parallel Corpus","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2512.18834","title":"Mix, MinHash, and Match: Cross-Source Agreement for Multilingual Pretraining Datasets","created":"2025-12-21","cited_by_count":1,"area":null},{"id":"2608.18094","title":"NE-BERT: A Multilingual Language Model for Nine Northeast Indian Languages","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2311.13475","title":"Machine Translation to Control Formality Features in the Target Language","created":"2023-11-22","cited_by_count":0,"area":null},{"id":"2404.11349","title":"TeClass: A Human-Annotated Relevance-based Headline Classification and Generation Dataset for Telugu","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2406.17801","title":"A multi-speaker multi-lingual voice cloning system based on vits2 for limmits 2024 challenge","created":"2024-06-22","cited_by_count":0,"area":null},{"id":"2411.06850","title":"1-800-SHARED-TASKS @ NLU of Devanagari Script Languages: Detection of Language, Hate Speech, and Targets using LLMs","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2412.10805","title":"Are Language Models Agnostic to Linguistically Grounded Perturbations? A Case Study of Indic Languages","created":"2024-12-14","cited_by_count":0,"area":null},{"id":"2507.04966","title":"LAPS-Diff: A Diffusion-Based Framework for Singing Voice Synthesis With Language Aware Prosody-Style Guided Learning","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2508.01486","title":"Human-Centered Supervision for Sentiment Analysis in Telugu: A Systematic Inquiry Beyond Accuracy","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2510.25273","title":"Adapting Small Language Models to Low-Resource Domains: A Case Study in Hindi Tourism QA","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2511.05324","title":"Evaluating Subword Tokenization Techniques for Bengali: A Benchmark Study with BengaliBPE","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2511.11309","title":"destroR: A Benchmark and Adversarial-Training Defense for Bangla Transfer Models under Meaning-Preserving Attacks","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2601.06041","title":"Lexical and Statistical Analysis of Bangla Newspaper and Literature: A Corpus-Driven Study on Diversity, Readability, and NLP Adaptation","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2601.10161","title":"AWED-PIPER: Agents, Web Applications & Expert Detectors for Personally Identifiable Information Protection & Fine-grained Named Entity Recognition across 36 languages for 6.6 Billion Speakers","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.10205","title":"One Instruction Does Not Fit All: How Well Do Embeddings Align Personas and Instructions in Low-Resource Indian Languages?","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.10388","title":"INDIC DIALECT: A Multi Task Benchmark to Evaluate and Translate in Indian Language Dialects","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.17764","title":"Cross-Lingual Probing and Community-Grounded Analysis of Gender Bias in Low-Resource Bengali","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2603.18579","title":"ICE: Intervention-Consistent Explanation Evaluation with Statistical Grounding for LLMs","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.29221","title":"SiPaKosa: A Comprehensive Corpus of Canonical and Classical Buddhist Texts in Sinhala and Pali","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2607.06544","title":"Rethinking Indic AI from a Lens of Cultural Heritage Preservation","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.21780","title":"Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.15535","title":"L3Cube-IndicQuest v2: A Large-Scale Multilingual Benchmark for Evaluating Factual Knowledge of Large Language Models Across Indic Languages","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.17325","title":"What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.18087","title":"SuTRA : Structurally-Unified Tokenization with Root Awareness","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2608.29919","title":"IndicDetect: Evaluating Cross-Lingual LLM-Generated Text Detection for Hindi, Telugu, and Tamil","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2608.29959","title":"Generative vs. Encoder Models for Multilingual NER: A Comprehensive Empirical Study on Naamapadam","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.01788","title":"VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.03597","title":"KhatianDoc: A Human-Verified Benchmark Diagnosing Multimodal LLM Failure on Bengali Legal Land Records","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.19879","title":"V\\={a}kQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22138","title":"Does the Truthfulness Signal Survive Code-Mixing? Probing Hidden States for Hallucination Detection in Hinglish","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2610.13121","title":"BenCoDiC: A Large-Scale Contextual Cyberbullying Corpus for Bengali Political News Discourse FULL VERSION","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.18818","title":"Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19190","title":"NEPSEE: A Double-Annotated Benchmark for Nepali Sentiment Analysis","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}